diff options
| -rw-r--r-- | ChangeLog | 6 | ||||
| -rw-r--r-- | lib/csv.rb | 1892 | ||||
| -rw-r--r-- | test/csv/line_endings.gz | bin | 0 -> 59 bytes | |||
| -rw-r--r-- | test/csv/tc_csv_parsing.rb | 164 | ||||
| -rw-r--r-- | test/csv/tc_csv_writing.rb | 96 | ||||
| -rw-r--r-- | test/csv/tc_data_converters.rb | 260 | ||||
| -rw-r--r-- | test/csv/tc_features.rb | 177 | ||||
| -rw-r--r-- | test/csv/tc_headers.rb | 261 | ||||
| -rw-r--r-- | test/csv/tc_interface.rb | 235 | ||||
| -rw-r--r-- | test/csv/tc_row.rb | 289 | ||||
| -rw-r--r-- | test/csv/tc_serialization.rb | 155 | ||||
| -rw-r--r-- | test/csv/tc_table.rb | 392 | ||||
| -rw-r--r-- | test/csv/ts_all.rb | 19 |
13 files changed, 3946 insertions, 0 deletions
@@ -1,3 +1,9 @@ +Tue Dec 25 11:45:34 2007 James Edward Gray II <jeg2@ruby-lang.org> + + * lib/csv.rb: Import the FasterCSV source as the new CSV class. + + * test/csv/*: Added all applicable tests from FasterCSV. + Tue Dec 25 11:33:52 2007 Nobuyoshi Nakada <nobu@ruby-lang.org> * error.c (report_bug): uses ruby_description. diff --git a/lib/csv.rb b/lib/csv.rb new file mode 100644 index 0000000000..a37bc700b2 --- /dev/null +++ b/lib/csv.rb @@ -0,0 +1,1892 @@ +#!/usr/local/bin/ruby -w + +# = csv.rb -- CSV Reading and Writing +# +# Created by James Edward Gray II on 2005-10-31. +# Copyright 2005 James Edward Gray II. You can redistribute or modify this code +# under the terms of Ruby's license. +# +# See CSV for documentation. +# +# == Description +# +# Welcome to the new and improved CSV. +# +# This version of the CSV library began its life as FasterCSV. FasterCSV was +# intended as a replacement to Ruby's then standard CSV library. It was +# designed to address concerns users of that library had and it had three +# primary goals: +# +# 1. Be significantly faster than CSV while remaining a pure Ruby library. +# 2. Use a smaller and easier to maintain code base. (FasterCSV eventually +# grew larger, was also but considerably richer in features. The parsing +# core remains quite small.) +# 3. Improve on the CSV interface. +# +# Obviously, the last one is subjective. I did try to defer to the original +# interface whenever I didn't have a compelling reason to change it though, so +# hopefully this won't be too radically different. +# +# We must have met our goals because FasterCSV was renamed to CSV and replaced +# the original library. +# +# == What's Different From the Old CSV? +# +# I'm sure I'll miss something, but I'll try to mention most of the major +# differences I am aware of, to help others quickly get up to speed: +# +# === CSV Parsing +# +# * This library has a stricter parser and will throw MalformedCSVErrors on +# problematic data. +# * This library has a less liberal idea of a line ending than CSV. What you +# set as the <tt>:row_sep</tt> is law. It can auto-detect your line endings +# though. +# * The old library returned empty lines as <tt>[nil]</tt>. This library calls +# them <tt>[]</tt>. +# * This library has a much faster parser. +# +# === Interface +# +# * CSV now uses Hash-style parameters to set options. +# * CSV no longer has generate_row() or parse_row(). +# * The old CSV's Reader and Writer classes have been dropped. +# * CSV::open() is now more like Ruby's open(). +# * CSV objects now support most standard IO methods. +# * CSV now has a new() method used to wrap objects like String and IO for +# reading and writing. +# * CSV::generate() is different from the old method. +# * CSV no longer supports partial reads. It works line-by-line. +# * CSV no longer allows the instance methods to override the separators for +# performance reasons. They must be set in the constructor. +# +# If you use this library and find yourself missing any functionality I have +# trimmed, please {let me know}[mailto:james@grayproductions.net]. +# +# == Documentation +# +# See CSV for documentation. +# +# == What is CSV, really? +# +# CSV maintains a pretty strict definition of CSV taken directly from +# {the RFC}[http://www.ietf.org/rfc/rfc4180.txt]. I relax the rules in only one +# place and that is to make using this library easier. CSV will parse all valid +# CSV. +# +# What you don't want to do is feed CSV invalid data. Because of the way the +# CSV format works, it's common for a parser to need to read until the end of +# the file to be sure a field is invalid. This eats a lot of time and memory. +# +# Luckily, when working with invalid CSV, Ruby's built-in methods will almost +# always be superior in every way. For example, parsing non-quoted fields is as +# easy as: +# +# data.split(",") +# +# == Questions and/or Comments +# +# Feel free to email {James Edward Gray II}[mailto:james@grayproductions.net] +# with any questions. + +require "forwardable" +require "English" +require "enumerator" +require "date" +require "stringio" + +# +# This class provides a complete interface to CSV files and data. It offers +# tools to enable you to read and write to and from Strings or IO objects, as +# needed. +# +# == Reading +# +# === From a File +# +# ==== A Line at a Time +# +# CSV.foreach("path/to/file.csv") do |row| +# # use row here... +# end +# +# ==== All at Once +# +# arr_of_arrs = CSV.read("path/to/file.csv") +# +# === From a String +# +# ==== A Line at a Time +# +# CSV.parse("CSV,data,String") do |row| +# # use row here... +# end +# +# ==== All at Once +# +# arr_of_arrs = CSV.parse("CSV,data,String") +# +# == Writing +# +# === To a File +# +# CSV.open("path/to/file.csv", "w") do |csv| +# csv << ["row", "of", "CSV", "data"] +# csv << ["another", "row"] +# # ... +# end +# +# === To a String +# +# csv_string = CSV.generate do |csv| +# csv << ["row", "of", "CSV", "data"] +# csv << ["another", "row"] +# # ... +# end +# +# == Convert a Single Line +# +# csv_string = ["CSV", "data"].to_csv # to CSV +# csv_array = "CSV,String".parse_csv # from CSV +# +# == Shortcut Interface +# +# CSV { |csv_out| csv_out << %w{my data here} } # to $stdout +# CSV(csv = "") { |csv_str| csv_str << %w{my data here} } # to a String +# CSV($stderr) { |csv_err| csv_err << %w{my data here} } # to $stderr +# +class CSV + # The version of the installed library. + VERSION = "2.0.0".freeze + + # + # A CSV::Row is part Array and part Hash. It retains an order for the fields + # and allows duplicates just as an Array would, but also allows you to access + # fields by name just as you could if they were in a Hash. + # + # All rows returned by CSV will be constructed from this class, if header row + # processing is activated. + # + class Row + # + # Construct a new CSV::Row from +headers+ and +fields+, which are expected + # to be Arrays. If one Array is shorter than the other, it will be padded + # with +nil+ objects. + # + # The optional +header_row+ parameter can be set to +true+ to indicate, via + # CSV::Row.header_row?() and CSV::Row.field_row?(), that this is a header + # row. Otherwise, the row is assumes to be a field row. + # + # A CSV::Row object supports the following Array methods through delegation: + # + # * empty?() + # * length() + # * size() + # + def initialize(headers, fields, header_row = false) + @header_row = header_row + + # handle extra headers or fields + @row = if headers.size > fields.size + headers.zip(fields) + else + fields.zip(headers).map { |pair| pair.reverse } + end + end + + # Internal data format used to compare equality. + attr_reader :row + protected :row + + ### Array Delegation ### + + extend Forwardable + def_delegators :@row, :empty?, :length, :size + + # Returns +true+ if this is a header row. + def header_row? + @header_row + end + + # Returns +true+ if this is a field row. + def field_row? + not header_row? + end + + # Returns the headers of this row. + def headers + @row.map { |pair| pair.first } + end + + # + # :call-seq: + # field( header ) + # field( header, offset ) + # field( index ) + # + # This method will fetch the field value by +header+ or +index+. If a field + # is not found, +nil+ is returned. + # + # When provided, +offset+ ensures that a header match occurrs on or later + # than the +offset+ index. You can use this to find duplicate headers, + # without resorting to hard-coding exact indices. + # + def field(header_or_index, minimum_index = 0) + # locate the pair + finder = header_or_index.is_a?(Integer) ? :[] : :assoc + pair = @row[minimum_index..-1].send(finder, header_or_index) + + # return the field if we have a pair + pair.nil? ? nil : pair.last + end + alias_method :[], :field + + # + # :call-seq: + # []=( header, value ) + # []=( header, offset, value ) + # []=( index, value ) + # + # Looks up the field by the semantics described in CSV::Row.field() and + # assigns the +value+. + # + # Assigning past the end of the row with an index will set all pairs between + # to <tt>[nil, nil]</tt>. Assigning to an unused header appends the new + # pair. + # + def []=(*args) + value = args.pop + + if args.first.is_a? Integer + if @row[args.first].nil? # extending past the end with index + @row[args.first] = [nil, value] + @row.map! { |pair| pair.nil? ? [nil, nil] : pair } + else # normal index assignment + @row[args.first][1] = value + end + else + index = index(*args) + if index.nil? # appending a field + self << [args.first, value] + else # normal header assignment + @row[index][1] = value + end + end + end + + # + # :call-seq: + # <<( field ) + # <<( header_and_field_array ) + # <<( header_and_field_hash ) + # + # If a two-element Array is provided, it is assumed to be a header and field + # and the pair is appended. A Hash works the same way with the key being + # the header and the value being the field. Anything else is assumed to be + # a lone field which is appended with a +nil+ header. + # + # This method returns the row for chaining. + # + def <<(arg) + if arg.is_a?(Array) and arg.size == 2 # appending a header and name + @row << arg + elsif arg.is_a?(Hash) # append header and name pairs + arg.each { |pair| @row << pair } + else # append field value + @row << [nil, arg] + end + + self # for chaining + end + + # + # A shortcut for appending multiple fields. Equivalent to: + # + # args.each { |arg| csv_row << arg } + # + # This method returns the row for chaining. + # + def push(*args) + args.each { |arg| self << arg } + + self # for chaining + end + + # + # :call-seq: + # delete( header ) + # delete( header, offset ) + # delete( index ) + # + # Used to remove a pair from the row by +header+ or +index+. The pair is + # located as described in CSV::Row.field(). The deleted pair is returned, + # or +nil+ if a pair could not be found. + # + def delete(header_or_index, minimum_index = 0) + if header_or_index.is_a? Integer # by index + @row.delete_at(header_or_index) + else # by header + @row.delete_at(index(header_or_index, minimum_index)) + end + end + + # + # The provided +block+ is passed a header and field for each pair in the row + # and expected to return +true+ or +false+, depending on whether the pair + # should be deleted. + # + # This method returns the row for chaining. + # + def delete_if(&block) + @row.delete_if(&block) + + self # for chaining + end + + # + # This method accepts any number of arguments which can be headers, indices, + # Ranges of either, or two-element Arrays containing a header and offset. + # Each argument will be replaced with a field lookup as described in + # CSV::Row.field(). + # + # If called with no arguments, all fields are returned. + # + def fields(*headers_and_or_indices) + if headers_and_or_indices.empty? # return all fields--no arguments + @row.map { |pair| pair.last } + else # or work like values_at() + headers_and_or_indices.inject(Array.new) do |all, h_or_i| + all + if h_or_i.is_a? Range + index_begin = h_or_i.begin.is_a?(Integer) ? h_or_i.begin : + index(h_or_i.begin) + index_end = h_or_i.end.is_a?(Integer) ? h_or_i.end : + index(h_or_i.end) + new_range = h_or_i.exclude_end? ? (index_begin...index_end) : + (index_begin..index_end) + fields.values_at(new_range) + else + [field(*Array(h_or_i))] + end + end + end + end + alias_method :values_at, :fields + + # + # :call-seq: + # index( header ) + # index( header, offset ) + # + # This method will return the index of a field with the provided +header+. + # The +offset+ can be used to locate duplicate header names, as described in + # CSV::Row.field(). + # + def index(header, minimum_index = 0) + # find the pair + index = headers[minimum_index..-1].index(header) + # return the index at the right offset, if we found one + index.nil? ? nil : index + minimum_index + end + + # Returns +true+ if +name+ is a header for this row, and +false+ otherwise. + def header?(name) + headers.include? name + end + alias_method :include?, :header? + + # + # Returns +true+ if +data+ matches a field in this row, and +false+ + # otherwise. + # + def field?(data) + fields.include? data + end + + include Enumerable + + # + # Yields each pair of the row as header and field tuples (much like + # iterating over a Hash). + # + # Support for Enumerable. + # + # This method returns the row for chaining. + # + def each(&block) + @row.each(&block) + + self # for chaining + end + + # + # Returns +true+ if this row contains the same headers and fields in the + # same order as +other+. + # + def ==(other) + @row == other.row + end + + # + # Collapses the row into a simple Hash. Be warning that this discards field + # order and clobbers duplicate fields. + # + def to_hash + # flatten just one level of the internal Array + Hash[*@row.inject(Array.new) { |ary, pair| ary.push(*pair) }] + end + + # + # Returns the row as a CSV String. Headers are not used. Equivalent to: + # + # csv_row.fields.to_csv( options ) + # + def to_csv(options = Hash.new) + fields.to_csv(options) + end + alias_method :to_s, :to_csv + end + + # + # A CSV::Table is a two-dimensional data structure for representing CSV + # documents. Tables allow you to work with the data by row or column, + # manipulate the data, and even convert the results back to CSV, if needed. + # + # All tables returned by CSV will be constructed from this class, if header + # row processing is activated. + # + class Table + # + # Construct a new CSV::Table from +array_of_rows+, which are expected + # to be CSV::Row objects. All rows are assumed to have the same headers. + # + # A CSV::Table object supports the following Array methods through + # delegation: + # + # * empty?() + # * length() + # * size() + # + def initialize(array_of_rows) + @table = array_of_rows + @mode = :col_or_row + end + + # The current access mode for indexing and iteration. + attr_reader :mode + + # Internal data format used to compare equality. + attr_reader :table + protected :table + + ### Array Delegation ### + + extend Forwardable + def_delegators :@table, :empty?, :length, :size + + # + # Returns a duplicate table object, in column mode. This is handy for + # chaining in a single call without changing the table mode, but be aware + # that this method can consume a fair amount of memory for bigger data sets. + # + # This method returns the duplicate table for chaining. Don't chain + # destructive methods (like []=()) this way though, since you are working + # with a duplicate. + # + def by_col + self.class.new(@table.dup).by_col! + end + + # + # Switches the mode of this table to column mode. All calls to indexing and + # iteration methods will work with columns until the mode is changed again. + # + # This method returns the table and is safe to chain. + # + def by_col! + @mode = :col + + self + end + + # + # Returns a duplicate table object, in mixed mode. This is handy for + # chaining in a single call without changing the table mode, but be aware + # that this method can consume a fair amount of memory for bigger data sets. + # + # This method returns the duplicate table for chaining. Don't chain + # destructive methods (like []=()) this way though, since you are working + # with a duplicate. + # + def by_col_or_row + self.class.new(@table.dup).by_col_or_row! + end + + # + # Switches the mode of this table to mixed mode. All calls to indexing and + # iteration methods will use the default intelligent indexing system until + # the mode is changed again. In mixed mode an index is assumed to be a row + # reference while anything else is assumed to be column access by headers. + # + # This method returns the table and is safe to chain. + # + def by_col_or_row! + @mode = :col_or_row + + self + end + + # + # Returns a duplicate table object, in row mode. This is handy for chaining + # in a single call without changing the table mode, but be aware that this + # method can consume a fair amount of memory for bigger data sets. + # + # This method returns the duplicate table for chaining. Don't chain + # destructive methods (like []=()) this way though, since you are working + # with a duplicate. + # + def by_row + self.class.new(@table.dup).by_row! + end + + # + # Switches the mode of this table to row mode. All calls to indexing and + # iteration methods will work with rows until the mode is changed again. + # + # This method returns the table and is safe to chain. + # + def by_row! + @mode = :row + + self + end + + # + # Returns the headers for the first row of this table (assumed to match all + # other rows). An empty Array is returned for empty tables. + # + def headers + if @table.empty? + Array.new + else + @table.first.headers + end + end + + # + # In the default mixed mode, this method returns rows for index access and + # columns for header access. You can force the index association by first + # calling by_col!() or by_row!(). + # + # Columns are returned as an Array of values. Altering that Array has no + # effect on the table. + # + def [](index_or_header) + if @mode == :row or # by index + (@mode == :col_or_row and index_or_header.is_a? Integer) + @table[index_or_header] + else # by header + @table.map { |row| row[index_or_header] } + end + end + + # + # In the default mixed mode, this method assigns rows for index access and + # columns for header access. You can force the index association by first + # calling by_col!() or by_row!(). + # + # Rows may be set to an Array of values (which will inherit the table's + # headers()) or a CSV::Row. + # + # Columns may be set to a single value, which is copied to each row of the + # column, or an Array of values. Arrays of values are assigned to rows top + # to bottom in row major order. Excess values are ignored and if the Array + # does not have a value for each row the extra rows will receive a +nil+. + # + # Assigning to an existing column or row clobbers the data. Assigning to + # new columns creates them at the right end of the table. + # + def []=(index_or_header, value) + if @mode == :row or # by index + (@mode == :col_or_row and index_or_header.is_a? Integer) + if value.is_a? Array + @table[index_or_header] = Row.new(headers, value) + else + @table[index_or_header] = value + end + else # set column + if value.is_a? Array # multiple values + @table.each_with_index do |row, i| + if row.header_row? + row[index_or_header] = index_or_header + else + row[index_or_header] = value[i] + end + end + else # repeated value + @table.each do |row| + if row.header_row? + row[index_or_header] = index_or_header + else + row[index_or_header] = value + end + end + end + end + end + + # + # The mixed mode default is to treat a list of indices as row access, + # returning the rows indicated. Anything else is considered columnar + # access. For columnar access, the return set has an Array for each row + # with the values indicated by the headers in each Array. You can force + # column or row mode using by_col!() or by_row!(). + # + # You cannot mix column and row access. + # + def values_at(*indices_or_headers) + if @mode == :row or # by indices + ( @mode == :col_or_row and indices_or_headers.all? do |index| + index.is_a?(Integer) or + ( index.is_a?(Range) and + index.first.is_a?(Integer) and + index.last.is_a?(Integer) ) + end ) + @table.values_at(*indices_or_headers) + else # by headers + @table.map { |row| row.values_at(*indices_or_headers) } + end + end + + # + # Adds a new row to the bottom end of this table. You can provide an Array, + # which will be converted to a CSV::Row (inheriting the table's headers()), + # or a CSV::Row. + # + # This method returns the table for chaining. + # + def <<(row_or_array) + if row_or_array.is_a? Array # append Array + @table << Row.new(headers, row_or_array) + else # append Row + @table << row_or_array + end + + self # for chaining + end + + # + # A shortcut for appending multiple rows. Equivalent to: + # + # rows.each { |row| self << row } + # + # This method returns the table for chaining. + # + def push(*rows) + rows.each { |row| self << row } + + self # for chaining + end + + # + # Removes and returns the indicated column or row. In the default mixed + # mode indices refer to rows and everything else is assumed to be a column + # header. Use by_col!() or by_row!() to force the lookup. + # + def delete(index_or_header) + if @mode == :row or # by index + (@mode == :col_or_row and index_or_header.is_a? Integer) + @table.delete_at(index_or_header) + else # by header + @table.map { |row| row.delete(index_or_header).last } + end + end + + # + # Removes any column or row for which the block returns +true+. In the + # default mixed mode or row mode, iteration is the standard row major + # walking of rows. In column mode, interation will +yield+ two element + # tuples containing the column name and an Array of values for that column. + # + # This method returns the table for chaining. + # + def delete_if(&block) + if @mode == :row or @mode == :col_or_row # by index + @table.delete_if(&block) + else # by header + to_delete = Array.new + headers.each_with_index do |header, i| + to_delete << header if block[[header, self[header]]] + end + to_delete.map { |header| delete(header) } + end + + self # for chaining + end + + include Enumerable + + # + # In the default mixed mode or row mode, iteration is the standard row major + # walking of rows. In column mode, interation will +yield+ two element + # tuples containing the column name and an Array of values for that column. + # + # This method returns the table for chaining. + # + def each(&block) + if @mode == :col + headers.each { |header| block[[header, self[header]]] } + else + @table.each(&block) + end + + self # for chaining + end + + # Returns +true+ if all rows of this table ==() +other+'s rows. + def ==(other) + @table == other.table + end + + # + # Returns the table as an Array of Arrays. Headers will be the first row, + # then all of the field rows will follow. + # + def to_a + @table.inject([headers]) do |array, row| + if row.header_row? + array + else + array + [row.fields] + end + end + end + + # + # Returns the table as a complete CSV String. Headers will be listed first, + # then all of the field rows. + # + def to_csv(options = Hash.new) + @table.inject([headers.to_csv(options)]) do |rows, row| + if row.header_row? + rows + else + rows + [row.fields.to_csv(options)] + end + end.join + end + alias_method :to_s, :to_csv + end + + # The error thrown when the parser encounters illegal CSV formatting. + class MalformedCSVError < RuntimeError; end + + # + # A FieldInfo Struct contains details about a field's position in the data + # source it was read from. CSV will pass this Struct to some blocks that make + # decisions based on field structure. See CSV.convert_fields() for an + # example. + # + # <b><tt>index</tt></b>:: The zero-based index of the field in its row. + # <b><tt>line</tt></b>:: The line of the data source this row is from. + # <b><tt>header</tt></b>:: The header for the column, when available. + # + FieldInfo = Struct.new(:index, :line, :header) + + # A Regexp used to find and convert some common Date formats. + DateMatcher = / \A(?: (\w+,?\s+)?\w+\s+\d{1,2},?\s+\d{2,4} | + \d{4}-\d{2}-\d{2} )\z /x + # A Regexp used to find and convert some common DateTime formats. + DateTimeMatcher = + / \A(?: (\w+,?\s+)?\w+\s+\d{1,2}\s+\d{1,2}:\d{1,2}:\d{1,2},?\s+\d{2,4} | + \d{4}-\d{2}-\d{2}\s\d{2}:\d{2}:\d{2} )\z /x + # + # This Hash holds the built-in converters of CSV that can be accessed by name. + # You can select Converters with CSV.convert() or through the +options+ Hash + # passed to CSV::new(). + # + # <b><tt>:integer</tt></b>:: Converts any field Integer() accepts. + # <b><tt>:float</tt></b>:: Converts any field Float() accepts. + # <b><tt>:numeric</tt></b>:: A combination of <tt>:integer</tt> + # and <tt>:float</tt>. + # <b><tt>:date</tt></b>:: Converts any field Date::parse() accepts. + # <b><tt>:date_time</tt></b>:: Converts any field DateTime::parse() accepts. + # <b><tt>:all</tt></b>:: All built-in converters. A combination of + # <tt>:date_time</tt> and <tt>:numeric</tt>. + # + # This Hash is intetionally left unfrozen and users should feel free to add + # values to it that can be accessed by all CSV objects. + # + # To add a combo field, the value should be an Array of names. Combo fields + # can be nested with other combo fields. + # + Converters = { :integer => lambda { |f| Integer(f) rescue f }, + :float => lambda { |f| Float(f) rescue f }, + :numeric => [:integer, :float], + :date => lambda { |f| + f =~ DateMatcher ? (Date.parse(f) rescue f) : f + }, + :date_time => lambda { |f| + f =~ DateTimeMatcher ? (DateTime.parse(f) rescue f) : f + }, + :all => [:date_time, :numeric] } + + # + # This Hash holds the built-in header converters of CSV that can be accessed + # by name. You can select HeaderConverters with CSV.header_convert() or + # through the +options+ Hash passed to CSV::new(). + # + # <b><tt>:downcase</tt></b>:: Calls downcase() on the header String. + # <b><tt>:symbol</tt></b>:: The header String is downcased, spaces are + # replaced with underscores, non-word characters + # are dropped, and finally to_sym() is called. + # + # This Hash is intetionally left unfrozen and users should feel free to add + # values to it that can be accessed by all CSV objects. + # + # To add a combo field, the value should be an Array of names. Combo fields + # can be nested with other combo fields. + # + HeaderConverters = { + :downcase => lambda { |h| h.downcase }, + :symbol => lambda { |h| + h.downcase.tr(" ", "_").delete("^a-z0-9_").to_sym + } + } + + # + # The options used when no overrides are given by calling code. They are: + # + # <b><tt>:col_sep</tt></b>:: <tt>","</tt> + # <b><tt>:row_sep</tt></b>:: <tt>:auto</tt> + # <b><tt>:quote_char</tt></b>:: <tt>'"'</tt> + # <b><tt>:converters</tt></b>:: +nil+ + # <b><tt>:unconverted_fields</tt></b>:: +nil+ + # <b><tt>:headers</tt></b>:: +false+ + # <b><tt>:return_headers</tt></b>:: +false+ + # <b><tt>:header_converters</tt></b>:: +nil+ + # <b><tt>:skip_blanks</tt></b>:: +false+ + # <b><tt>:force_quotes</tt></b>:: +false+ + # + DEFAULT_OPTIONS = { :col_sep => ",", + :row_sep => :auto, + :quote_char => '"', + :converters => nil, + :unconverted_fields => nil, + :headers => false, + :return_headers => false, + :header_converters => nil, + :skip_blanks => false, + :force_quotes => false }.freeze + + # + # This method allows you to serialize an Array of Ruby objects to a String or + # File of CSV data. This is not as powerful as Marshal or YAML, but perhaps + # useful for spreadsheet and database interaction. + # + # Out of the box, this method is intended to work with simple data objects or + # Structs. It will serialize a list of instance variables and/or + # Struct.members(). + # + # If you need need more complicated serialization, you can control the process + # by adding methods to the class to be serialized. + # + # A class method csv_meta() is responsible for returning the first row of the + # document (as an Array). This row is considered to be a Hash of the form + # key_1,value_1,key_2,value_2,... CSV::load() expects to find a class key + # with a value of the stringified class name and CSV::dump() will create this, + # if you do not define this method. This method is only called on the first + # object of the Array. + # + # The next method you can provide is an instance method called csv_headers(). + # This method is expected to return the second line of the document (again as + # an Array), which is to be used to give each column a header. By default, + # CSV::load() will set an instance variable if the field header starts with an + # @ character or call send() passing the header as the method name and + # the field value as an argument. This method is only called on the first + # object of the Array. + # + # Finally, you can provide an instance method called csv_dump(), which will + # be passed the headers. This should return an Array of fields that can be + # serialized for this object. This method is called once for every object in + # the Array. + # + # The +io+ parameter can be used to serialize to a File, and +options+ can be + # anything CSV::new() accepts. + # + def self.dump(ary_of_objs, io = "", options = Hash.new) + obj_template = ary_of_objs.first + + csv = new(io, options) + + # write meta information + begin + csv << obj_template.class.csv_meta + rescue NoMethodError + csv << [:class, obj_template.class] + end + + # write headers + begin + headers = obj_template.csv_headers + rescue NoMethodError + headers = obj_template.instance_variables.sort + if obj_template.class.ancestors.find { |cls| cls.to_s =~ /\AStruct\b/ } + headers += obj_template.members.map { |mem| "#{mem}=" }.sort + end + end + csv << headers + + # serialize each object + ary_of_objs.each do |obj| + begin + csv << obj.csv_dump(headers) + rescue NoMethodError + csv << headers.map do |var| + if var[0] == ?@ + obj.instance_variable_get(var) + else + obj[var[0..-2]] + end + end + end + end + + if io.is_a? String + csv.string + else + csv.close + end + end + + # + # :call-seq: + # filter( options = Hash.new ) { |row| ... } + # filter( input, options = Hash.new ) { |row| ... } + # filter( input, output, options = Hash.new ) { |row| ... } + # + # This method is a convenience for building Unix-like filters for CSV data. + # Each row is yielded to the provided block which can alter it as needed. + # After the block returns, the row is appended to +output+ altered or not. + # + # The +input+ and +output+ arguments can be anything CSV::new() accepts + # (generally String or IO objects). If not given, they default to + # <tt>ARGF</tt> and <tt>$stdout</tt>. + # + # The +options+ parameter is also filtered down to CSV::new() after some + # clever key parsing. Any key beginning with <tt>:in_</tt> or + # <tt>:input_</tt> will have that leading identifier stripped and will only + # be used in the +options+ Hash for the +input+ object. Keys starting with + # <tt>:out_</tt> or <tt>:output_</tt> affect only +output+. All other keys + # are assigned to both objects. + # + # The <tt>:output_row_sep</tt> +option+ defaults to + # <tt>$INPUT_RECORD_SEPARATOR</tt> (<tt>$/</tt>). + # + def self.filter(*args) + # parse options for input, output, or both + in_options, out_options = Hash.new, {:row_sep => $INPUT_RECORD_SEPARATOR} + if args.last.is_a? Hash + args.pop.each do |key, value| + case key.to_s + when /\Ain(?:put)?_(.+)\Z/ + in_options[$1.to_sym] = value + when /\Aout(?:put)?_(.+)\Z/ + out_options[$1.to_sym] = value + else + in_options[key] = value + out_options[key] = value + end + end + end + # build input and output wrappers + input = new(args.shift || ARGF, in_options) + output = new(args.shift || $stdout, out_options) + + # read, yield, write + input.each do |row| + yield row + output << row + end + end + + # + # This method is intended as the primary interface for reading CSV files. You + # pass a +path+ and any +options+ you wish to set for the read. Each row of + # file will be passed to the provided +block+ in turn. + # + # The +options+ parameter can be anything CSV::new() understands. + # + def self.foreach(path, options = Hash.new, &block) + open(path, options) do |csv| + csv.each(&block) + end + end + + # + # :call-seq: + # generate( str, options = Hash.new ) { |csv| ... } + # generate( options = Hash.new ) { |csv| ... } + # + # This method wraps a String you provide, or an empty default String, in a + # CSV object which is passed to the provided block. You can use the block to + # append CSV rows to the String and when the block exits, the final String + # will be returned. + # + # Note that a passed String *is* modfied by this method. Call dup() before + # passing if you need a new String. + # + # The +options+ parameter can be anthing CSV::new() understands. + # + def self.generate(*args) + # add a default empty String, if none was given + if args.first.is_a? String + io = StringIO.new(args.shift) + io.seek(0, IO::SEEK_END) + args.unshift(io) + else + args.unshift("") + end + csv = new(*args) # wrap + yield csv # yield for appending + csv.string # return final String + end + + # + # This method is a shortcut for converting a single row (Array) into a CSV + # String. + # + # The +options+ parameter can be anthing CSV::new() understands. + # + # The <tt>:row_sep</tt> +option+ defaults to <tt>$INPUT_RECORD_SEPARATOR</tt> + # (<tt>$/</tt>) when calling this method. + # + def self.generate_line(row, options = Hash.new) + options = {:row_sep => $INPUT_RECORD_SEPARATOR}.merge(options) + (new("", options) << row).string + end + + # + # This method will return a CSV instance, just like CSV::new(), but the + # instance will be cached and returned for all future calls to this method for + # the same +data+ object (tested by Object#object_id()) with the same + # +options+. + # + # If a block is given, the instance is passed to the block and the return + # value becomes the return value of the block. + # + def self.instance(data = $stdout, options = Hash.new) + # create a _signature_ for this method call, data object and options + sig = [data.object_id] + + options.values_at(*DEFAULT_OPTIONS.keys.sort_by { |sym| sym.to_s }) + + # fetch or create the instance for this signature + @@instances ||= Hash.new + instance = (@@instances[sig] ||= new(data, options)) + + if block_given? + yield instance # run block, if given, returning result + else + instance # or return the instance + end + end + + # + # This method is the reading counterpart to CSV::dump(). See that method for + # a detailed description of the process. + # + # You can customize loading by adding a class method called csv_load() which + # will be passed a Hash of meta information, an Array of headers, and an Array + # of fields for the object the method is expected to return. + # + # Remember that all fields will be Strings after this load. If you need + # something else, use +options+ to setup converters or provide a custom + # csv_load() implementation. + # + def self.load(io_or_str, options = Hash.new) + csv = new(io_or_str, options) + + # load meta information + meta = Hash[*csv.shift] + cls = meta["class"].split("::").inject(Object) do |c, const| + c.const_get(const) + end + + # load headers + headers = csv.shift + + # unserialize each object stored in the file + results = csv.inject(Array.new) do |all, row| + begin + obj = cls.csv_load(meta, headers, row) + rescue NoMethodError + obj = cls.allocate + headers.zip(row) do |name, value| + if name[0] == ?@ + obj.instance_variable_set(name, value) + else + obj.send(name, value) + end + end + end + all << obj + end + + csv.close unless io_or_str.is_a? String + + results + end + + # + # :call-seq: + # open( filename, mode="r", options = Hash.new ) { |csv| ... } + # open( filename, mode="r", options = Hash.new ) + # + # This method opens an IO object, and wraps that with CSV. This is intended + # as the primary interface for writing a CSV file. + # + # You may pass any +args+ Ruby's open() understands followed by an optional + # Hash containing any +options+ CSV::new() understands. + # + # This method works like Ruby's open() call, in that it will pass a CSV object + # to a provided block and close it when the block termminates, or it will + # return the CSV object when no block is provided. (*Note*: This is different + # from the Ruby 1.8 CSV library which passed rows to the block. Use + # CSV::foreach() for that behavior.) + # + # An opened CSV object will delegate to many IO methods, for convenience. You + # may call: + # + # * binmode() + # * close() + # * close_read() + # * close_write() + # * closed?() + # * eof() + # * eof?() + # * fcntl() + # * fileno() + # * flush() + # * fsync() + # * ioctl() + # * isatty() + # * pid() + # * pos() + # * reopen() + # * seek() + # * stat() + # * sync() + # * sync=() + # * tell() + # * to_i() + # * to_io() + # * tty?() + # + def self.open(*args) + # find the +options+ Hash + options = if args.last.is_a? Hash then args.pop else Hash.new end + # wrap a File opened with the remaining +args+ + csv = new(File.open(*args), options) + + # handle blocks like Ruby's open(), not like the CSV library + if block_given? + begin + yield csv + ensure + csv.close + end + else + csv + end + end + + # + # :call-seq: + # parse( str, options = Hash.new ) { |row| ... } + # parse( str, options = Hash.new ) + # + # This method can be used to easily parse CSV out of a String. You may either + # provide a +block+ which will be called with each row of the String in turn, + # or just use the returned Array of Arrays (when no +block+ is given). + # + # You pass your +str+ to read from, and an optional +options+ Hash containing + # anything CSV::new() understands. + # + def self.parse(*args, &block) + csv = new(*args) + if block.nil? # slurp contents, if no block is given + begin + csv.read + ensure + csv.close + end + else # or pass each row to a provided block + csv.each(&block) + end + end + + # + # This method is a shortcut for converting a single line of a CSV String into + # a into an Array. Note that if +line+ contains multiple rows, anything + # beyond the first row is ignored. + # + # The +options+ parameter can be anthing CSV::new() understands. + # + def self.parse_line(line, options = Hash.new) + new(line, options).shift + end + + # + # Use to slurp a CSV file into an Array of Arrays. Pass the +path+ to the + # file and any +options+ CSV::new() understands. + # + def self.read(path, options = Hash.new) + open(path, options) { |csv| csv.read } + end + + # Alias for CSV::read(). + def self.readlines(*args) + read(*args) + end + + # + # A shortcut for: + # + # CSV.read( path, { :headers => true, + # :converters => :numeric, + # :header_converters => :symbol }.merge(options) ) + # + def self.table(path, options = Hash.new) + read( path, { :headers => true, + :converters => :numeric, + :header_converters => :symbol }.merge(options) ) + end + + # + # This constructor will wrap either a String or IO object passed in +data+ for + # reading and/or writing. In addition to the CSV instance methods, several IO + # methods are delegated. (See CSV::open() for a complete list.) If you pass + # a String for +data+, you can later retrieve it (after writing to it, for + # example) with CSV.string(). + # + # Note that a wrapped String will be positioned at at the beginning (for + # reading). If you want it at the end (for writing), use CSV::generate(). + # If you want any other positioning, pass a preset StringIO object instead. + # + # You may set any reading and/or writing preferences in the +options+ Hash. + # Available options are: + # + # <b><tt>:col_sep</tt></b>:: The String placed between each field. + # <b><tt>:row_sep</tt></b>:: The String appended to the end of each + # row. This can be set to the special + # <tt>:auto</tt> setting, which requests + # that CSV automatically discover this + # from the data. Auto-discovery reads + # ahead in the data looking for the next + # <tt>"\r\n"</tt>, <tt>"\n"</tt>, or + # <tt>"\r"</tt> sequence. A sequence + # will be selected even if it occurs in + # a quoted field, assuming that you + # would have the same line endings + # there. If none of those sequences is + # found, +data+ is <tt>ARGF</tt>, + # <tt>STDIN</tt>, <tt>STDOUT</tt>, or + # <tt>STDERR</tt>, or the stream is only + # available for output, the default + # <tt>$INPUT_RECORD_SEPARATOR</tt> + # (<tt>$/</tt>) is used. Obviously, + # discovery takes a little time. Set + # manually if speed is important. + # <b><tt>:quote_char</tt></b>:: The character used to quote fields. + # This has to be a single character + # String. This is useful for + # application that incorrectly use + # <tt>'</tt> as the quote character + # instead of the correct <tt>"</tt>. + # CSV will always consider a double + # sequence this character to be an + # escaped quote. + # <b><tt>:converters</tt></b>:: An Array of names from the Converters + # Hash and/or lambdas that handle custom + # conversion. A single converter + # doesn't have to be in an Array. + # <b><tt>:unconverted_fields</tt></b>:: If set to +true+, an + # unconverted_fields() method will be + # added to all returned rows (Array or + # CSV::Row) that will return the fields + # as they were before convertion. Note + # that <tt>:headers</tt> supplied by + # Array or String were not fields of the + # document and thus will have an empty + # Array attached. + # <b><tt>:headers</tt></b>:: If set to <tt>:first_row</tt> or + # +true+, the initial row of the CSV + # file will be treated as a row of + # headers. If set to an Array, the + # contents will be used as the headers. + # If set to a String, the String is run + # through a call of CSV::parse_line() to + # produce an Array of headers. This + # setting causes CSV.shift() to return + # rows as CSV::Row objects instead of + # Arrays and CSV.read() to return + # CSV::Table objects instead of an Array + # of Arrays. + # <b><tt>:return_headers</tt></b>:: When +false+, header rows are silently + # swallowed. If set to +true+, header + # rows are returned in a CSV::Row object + # with identical headers and + # fields (save that the fields do not go + # through the converters). + # <b><tt>:header_converters</tt></b>:: Identical in functionality to + # <tt>:converters</tt> save that the + # conversions are only made to header + # rows. + # <b><tt>:skip_blanks</tt></b>:: When set to a +true+ value, CSV will + # skip over any rows with no content. + # <b><tt>:force_quotes</tt></b>:: When set to a +true+ value, CSV will + # quote all CSV fields it creates. + # + # See CSV::DEFAULT_OPTIONS for the default settings. + # + # Options cannot be overriden in the instance methods for performance reasons, + # so be sure to set what you want here. + # + def initialize(data, options = Hash.new) + # build the options for this read/write + options = DEFAULT_OPTIONS.merge(options) + + # create the IO object we will read from + @io = if data.is_a? String then StringIO.new(data) else data end + + init_separators(options) + init_parsers(options) + init_converters(options) + init_headers(options) + + unless options.empty? + raise ArgumentError, "Unknown options: #{options.keys.join(', ')}." + end + + # track our own lineno since IO gets confused about line-ends is CSV fields + @lineno = 0 + end + + # + # The line number of the last row read from this file. Fields with nested + # line-end characters will not affect this count. + # + attr_reader :lineno + + ### IO and StringIO Delegation ### + + extend Forwardable + def_delegators :@io, :binmode, :close, :close_read, :close_write, :closed?, + :eof, :eof?, :fcntl, :fileno, :flush, :fsync, :ioctl, + :isatty, :pid, :pos, :reopen, :seek, :stat, :string, + :sync, :sync=, :tell, :to_i, :to_io, :tty? + + # Rewinds the underlying IO object and resets CSV's lineno() counter. + def rewind + @headers = nil + @lineno = 0 + + @io.rewind + end + + ### End Delegation ### + + # + # The primary write method for wrapped Strings and IOs, +row+ (an Array or + # CSV::Row) is converted to CSV and appended to the data source. When a + # CSV::Row is passed, only the row's fields() are appended to the output. + # + # The data source must be open for writing. + # + def <<(row) + # handle CSV::Row objects and Hashes + row = case row + when self.class::Row then row.fields + when Hash then @headers.map { |header| row[header] } + else row + end + + @headers = row if header_row? + @lineno += 1 + + @io << row.map(&@quote).join(@col_sep) + @row_sep # quote and separate + + self # for chaining + end + alias_method :add_row, :<< + alias_method :puts, :<< + + # + # :call-seq: + # convert( name ) + # convert { |field| ... } + # convert { |field, field_info| ... } + # + # You can use this method to install a CSV::Converters built-in, or provide a + # block that handles a custom conversion. + # + # If you provide a block that takes one argument, it will be passed the field + # and is expected to return the converted value or the field itself. If your + # block takes two arguments, it will also be passed a FieldInfo Struct, + # containing details about the field. Again, the block should return a + # converted field or the field itself. + # + def convert(name = nil, &converter) + add_converter(:converters, self.class::Converters, name, &converter) + end + + # + # :call-seq: + # header_convert( name ) + # header_convert { |field| ... } + # header_convert { |field, field_info| ... } + # + # Identical to CSV.convert(), but for header rows. + # + # Note that this method must be called before header rows are read to have any + # effect. + # + def header_convert(name = nil, &converter) + add_converter( :header_converters, + self.class::HeaderConverters, + name, + &converter ) + end + + include Enumerable + + # + # Yields each row of the data source in turn. + # + # Support for Enumerable. + # + # The data source must be open for reading. + # + def each + while row = shift + yield row + end + end + + # + # Slurps the remaining rows and returns an Array of Arrays. + # + # The data source must be open for reading. + # + def read + rows = to_a + if @use_headers + Table.new(rows) + else + rows + end + end + alias_method :readlines, :read + + # Returns +true+ if the next row read will be a header row. + def header_row? + @use_headers and @headers.nil? + end + + # + # The primary read method for wrapped Strings and IOs, a single row is pulled + # from the data source, parsed and returned as an Array of fields (if header + # rows are not used) or a CSV::Row (when header rows are used). + # + # The data source must be open for reading. + # + def shift + ######################################################################### + ### This method is purposefully kept a bit long as simple conditional ### + ### checks are faster than numerous (expensive) method calls. ### + ######################################################################### + + # handle headers not based on document content + if header_row? and @return_headers and + [Array, String].include? @use_headers.class + if @unconverted_fields + return add_unconverted_fields(parse_headers, Array.new) + else + return parse_headers + end + end + + # begin with a blank line, so we can always add to it + line = "" + + # + # it can take multiple calls to <tt>@io.gets()</tt> to get a full line, + # because of \r and/or \n characters embedded in quoted fields + # + loop do + # add another read to the line + line += @io.gets(@row_sep) rescue return nil + # copy the line so we can chop it up in parsing + parse = line.dup + parse.sub!(@parsers[:line_end], "") + + # + # I believe a blank line should be an <tt>Array.new</tt>, not Ruby 1.8 + # CSV's <tt>[nil]</tt> + # + if parse.empty? + @lineno += 1 + if @skip_blanks + line = "" + next + elsif @unconverted_fields + return add_unconverted_fields(Array.new, Array.new) + elsif @use_headers + return self.class::Row.new(Array.new, Array.new) + else + return Array.new + end + end + + # + # shave leading empty fields if needed, because the main parser chokes + # on these + # + csv = if parse.sub!(@parsers[:leading_fields], "") + [nil] * ($&.length / @col_sep.length) + else + Array.new + end + # + # then parse the main fields with a hyper-tuned Regexp from + # Mastering Regular Expressions, Second Edition + # + parse.gsub!(@parsers[:csv_row]) do + csv << if $1.nil? # we found an unquoted field + if $2.empty? # switch empty unquoted fields to +nil+... + nil # for Ruby 1.8 CSV compatibility + else + # I decided to take a strict approach to CSV parsing... + if $2.count("\r\n").zero? # verify correctness of field... + $2 + else + # or throw an Exception + raise MalformedCSVError, "Unquoted fields do not allow " + + "\\r or \\n (line #{lineno + 1})." + end + end + else # we found a quoted field... + $1.gsub(@quote_char * 2, @quote_char) # unescape contents + end + "" # gsub!'s replacement, clear the field + end + + # if parse is empty?(), we found all the fields on the line... + if parse.empty? + @lineno += 1 + + # save fields unconverted fields, if needed... + unconverted = csv.dup if @unconverted_fields + + # convert fields, if needed... + csv = convert_fields(csv) unless @use_headers or @converters.empty? + # parse out header rows and handle CSV::Row conversions... + csv = parse_headers(csv) if @use_headers + + # inject unconverted fields and accessor, if requested... + if @unconverted_fields and not csv.respond_to? :unconverted_fields + add_unconverted_fields(csv, unconverted) + end + + # return the results + break csv + end + # if we're not empty?() but at eof?(), a quoted field wasn't closed... + if @io.eof? + raise MalformedCSVError, "Unclosed quoted field on line #{lineno + 1}." + end + # otherwise, we need to loop and pull some more data to complete the row + end + end + alias_method :gets, :shift + alias_method :readline, :shift + + private + + # + # Stores the indicated separators for later use. + # + # If auto-discovery was requested for <tt>@row_sep</tt>, this method will read + # ahead in the <tt>@io</tt> and try to find one. +ARGF+, +STDIN+, +STDOUT+, + # +STDERR+ and any stream open for output only with a default + # <tt>@row_sep</tt> of <tt>$INPUT_RECORD_SEPARATOR</tt> (<tt>$/</tt>). + # + # This method also establishes the quoting rules used for CSV output. + # + def init_separators(options) + # store the selected separators + @col_sep = options.delete(:col_sep) + @row_sep = options.delete(:row_sep) + @quote_char = options.delete(:quote_char) + + if @quote_char.length != 1 + raise ArgumentError, ":quote_char has to be a single character String" + end + + # automatically discover row separator when requested + if @row_sep == :auto + if [ARGF, STDIN, STDOUT, STDERR].include?(@io) or + (defined?(Zlib) and @io.class == Zlib::GzipWriter) + @row_sep = $INPUT_RECORD_SEPARATOR + else + begin + saved_pos = @io.pos # remember where we were + while @row_sep == :auto + # + # if we run out of data, it's probably a single line + # (use a sensible default) + # + if @io.eof? + @row_sep = $INPUT_RECORD_SEPARATOR + break + end + + # read ahead a bit + sample = @io.read(1024) + sample += @io.read(1) if sample[-1..-1] == "\r" and not @io.eof? + + # try to find a standard separator + if sample =~ /\r\n?|\n/ + @row_sep = $& + break + end + end + # tricky seek() clone to work around GzipReader's lack of seek() + @io.rewind + # reset back to the remembered position + while saved_pos > 1024 # avoid loading a lot of data into memory + @io.read(1024) + saved_pos -= 1024 + end + @io.read(saved_pos) if saved_pos.nonzero? + rescue IOError # stream not opened for reading + @row_sep = $INPUT_RECORD_SEPARATOR + end + end + end + + # establish quoting rules + do_quote = lambda do |field| + @quote_char + + String(field).gsub(@quote_char, @quote_char * 2) + + @quote_char + end + @quote = if options.delete(:force_quotes) + do_quote + else + lambda do |field| + if field.nil? # represent +nil+ fields as empty unquoted fields + "" + else + field = String(field) # Stringify fields + # represent empty fields as empty quoted fields + if field.empty? or + field.count("\r\n#{@col_sep}#{@quote_char}").nonzero? + do_quote.call(field) + else + field # unquoted field + end + end + end + end + end + + # Pre-compiles parsers and stores them by name for access during reads. + def init_parsers(options) + # store the parser behaviors + @skip_blanks = options.delete(:skip_blanks) + + # prebuild Regexps for faster parsing + esc_col_sep = Regexp.escape(@col_sep) + esc_row_sep = Regexp.escape(@row_sep) + esc_quote = Regexp.escape(@quote_char) + @parsers = { + :leading_fields => + /\A(?:#{esc_col_sep})+/, # for empty leading fields + :csv_row => + ### The Primary Parser ### + / \G(?:^|#{esc_col_sep}) # anchor the match + (?: #{esc_quote}( (?>[^#{esc_quote}]*) # find quoted fields + (?> #{esc_quote*2} + [^#{esc_quote}]* )* )#{esc_quote} + | # ... or ... + ([^#{esc_quote}#{esc_col_sep}]*) # unquoted fields + )/x, + ### End Primary Parser ### + :line_end => + /#{esc_row_sep}\z/ # safer than chomp!() + } + end + + # + # Loads any converters requested during construction. + # + # If +field_name+ is set <tt>:converters</tt> (the default) field converters + # are set. When +field_name+ is <tt>:header_converters</tt> header converters + # are added instead. + # + # The <tt>:unconverted_fields</tt> option is also actived for + # <tt>:converters</tt> calls, if requested. + # + def init_converters(options, field_name = :converters) + if field_name == :converters + @unconverted_fields = options.delete(:unconverted_fields) + end + + instance_variable_set("@#{field_name}", Array.new) + + # find the correct method to add the coverters + convert = method(field_name.to_s.sub(/ers\Z/, "")) + + # load converters + unless options[field_name].nil? + # allow a single converter not wrapped in an Array + unless options[field_name].is_a? Array + options[field_name] = [options[field_name]] + end + # load each converter... + options[field_name].each do |converter| + if converter.is_a? Proc # custom code block + convert.call(&converter) + else # by name + convert.call(converter) + end + end + end + + options.delete(field_name) + end + + # Stores header row settings and loads header converters, if needed. + def init_headers(options) + @use_headers = options.delete(:headers) + @return_headers = options.delete(:return_headers) + + # headers must be delayed until shift(), in case they need a row of content + @headers = nil + + init_converters(options, :header_converters) + end + + # + # The actual work method for adding converters, used by both CSV.convert() and + # CSV.header_convert(). + # + # This method requires the +var_name+ of the instance variable to place the + # converters in, the +const+ Hash to lookup named converters in, and the + # normal parameters of the CSV.convert() and CSV.header_convert() methods. + # + def add_converter(var_name, const, name = nil, &converter) + if name.nil? # custom converter + instance_variable_get("@#{var_name}") << converter + else # named converter + combo = const[name] + case combo + when Array # combo converter + combo.each do |converter_name| + add_converter(var_name, const, converter_name) + end + else # individual named converter + instance_variable_get("@#{var_name}") << combo + end + end + end + + # + # Processes +fields+ with <tt>@converters</tt>, or <tt>@header_converters</tt> + # if +headers+ is passed as +true+, returning the converted field set. Any + # converter that changes the field into something other than a String halts + # the pipeline of conversion for that field. This is primarily an efficiency + # shortcut. + # + def convert_fields(fields, headers = false) + # see if we are converting headers or fields + converters = headers ? @header_converters : @converters + + fields.enum_for(:each_with_index).map do |field, index| # map_with_index + converters.each do |converter| + field = if converter.arity == 1 # straight field converter + converter[field] + else # FieldInfo converter + header = @use_headers && !headers ? @headers[index] : nil + converter[field, FieldInfo.new(index, lineno, header)] + end + break unless field.is_a? String # short-curcuit pipeline for speed + end + field # return final state of each field, converted or original + end + end + + # + # This methods is used to turn a finished +row+ into a CSV::Row. Header rows + # are also dealt with here, either by returning a CSV::Row with identical + # headers and fields (save that the fields do not go through the converters) + # or by reading past them to return a field row. Headers are also saved in + # <tt>@headers</tt> for use in future rows. + # + # When +nil+, +row+ is assumed to be a header row not based on an actual row + # of the stream. + # + def parse_headers(row = nil) + if @headers.nil? # header row + @headers = case @use_headers # save headers + when Array then @use_headers # Array of headers + when String then self.class.parse_line(@use_headers) # CSV header String + else row # first row headers + end + + # prepare converted and unconverted copies + row = @headers if row.nil? + @headers = convert_fields(@headers, true) + + if @return_headers # return headers + return self.class::Row.new(@headers, row, true) + elsif not [Array, String].include? @use_headers.class # skip to field row + return shift + end + end + + self.class::Row.new(@headers, convert_fields(row)) # field row + end + + # + # Thiw methods injects an instance variable <tt>unconverted_fields</tt> into + # +row+ and an accessor method for it called unconverted_fields(). The + # variable is set to the contents of +fields+. + # + def add_unconverted_fields(row, fields) + class << row + attr_reader :unconverted_fields + end + row.instance_eval { @unconverted_fields = fields } + row + end +end + +# Another name for CSV::instance(). +def CSV(*args, &block) + CSV.instance(*args, &block) +end + +class Array + # Equivalent to <tt>CSV::generate_line(self, options)</tt>. + def to_csv(options = Hash.new) + CSV.generate_line(self, options) + end +end + +class String + # Equivalent to <tt>CSV::parse_line(self, options)</tt>. + def parse_csv(options = Hash.new) + CSV.parse_line(self, options) + end +end diff --git a/test/csv/line_endings.gz b/test/csv/line_endings.gz Binary files differnew file mode 100644 index 0000000000..39e1729ee4 --- /dev/null +++ b/test/csv/line_endings.gz diff --git a/test/csv/tc_csv_parsing.rb b/test/csv/tc_csv_parsing.rb new file mode 100644 index 0000000000..9eb2e398d4 --- /dev/null +++ b/test/csv/tc_csv_parsing.rb @@ -0,0 +1,164 @@ +#!/usr/local/bin/ruby -w + +# tc_csv_parsing.rb +# +# Created by James Edward Gray II on 2005-10-31. +# Copyright 2005 James Edward Gray II. You can redistribute or modify this code +# under the terms of Ruby's license. + +require "test/unit" + +require "csv" + +# +# Following tests are my interpretation of the +# {CSV RCF}[http://www.ietf.org/rfc/rfc4180.txt]. I only deviate from that +# document in one place (intentionally) and that is to make the default row +# separator <tt>$/</tt>. +# +class TestCSVParsing < Test::Unit::TestCase + def test_mastering_regex_example + ex = %Q{Ten Thousand,10000, 2710 ,,"10,000","It's ""10 Grand"", baby",10K} + assert_equal( [ "Ten Thousand", "10000", " 2710 ", nil, "10,000", + "It's \"10 Grand\", baby", "10K" ], + CSV.parse_line(ex) ) + end + + # Old Ruby 1.8 CSV library tests. + def test_std_lib_csv + [ ["\t", ["\t"]], + ["foo,\"\"\"\"\"\",baz", ["foo", "\"\"", "baz"]], + ["foo,\"\"\"bar\"\"\",baz", ["foo", "\"bar\"", "baz"]], + ["\"\"\"\n\",\"\"\"\n\"", ["\"\n", "\"\n"]], + ["foo,\"\r\n\",baz", ["foo", "\r\n", "baz"]], + ["\"\"", [""]], + ["foo,\"\"\"\",baz", ["foo", "\"", "baz"]], + ["foo,\"\r.\n\",baz", ["foo", "\r.\n", "baz"]], + ["foo,\"\r\",baz", ["foo", "\r", "baz"]], + ["foo,\"\",baz", ["foo", "", "baz"]], + ["\",\"", [","]], + ["foo", ["foo"]], + [",,", [nil, nil, nil]], + [",", [nil, nil]], + ["foo,\"\n\",baz", ["foo", "\n", "baz"]], + ["foo,,baz", ["foo", nil, "baz"]], + ["\"\"\"\r\",\"\"\"\r\"", ["\"\r", "\"\r"]], + ["\",\",\",\"", [",", ","]], + ["foo,bar,", ["foo", "bar", nil]], + [",foo,bar", [nil, "foo", "bar"]], + ["foo,bar", ["foo", "bar"]], + [";", [";"]], + ["\t,\t", ["\t", "\t"]], + ["foo,\"\r\n\r\",baz", ["foo", "\r\n\r", "baz"]], + ["foo,\"\r\n\n\",baz", ["foo", "\r\n\n", "baz"]], + ["foo,\"foo,bar\",baz", ["foo", "foo,bar", "baz"]], + [";,;", [";", ";"]] ].each do |csv_test| + assert_equal(csv_test.last, CSV.parse_line(csv_test.first)) + end + + [ ["foo,\"\"\"\"\"\",baz", ["foo", "\"\"", "baz"]], + ["foo,\"\"\"bar\"\"\",baz", ["foo", "\"bar\"", "baz"]], + ["foo,\"\r\n\",baz", ["foo", "\r\n", "baz"]], + ["\"\"", [""]], + ["foo,\"\"\"\",baz", ["foo", "\"", "baz"]], + ["foo,\"\r.\n\",baz", ["foo", "\r.\n", "baz"]], + ["foo,\"\r\",baz", ["foo", "\r", "baz"]], + ["foo,\"\",baz", ["foo", "", "baz"]], + ["foo", ["foo"]], + [",,", [nil, nil, nil]], + [",", [nil, nil]], + ["foo,\"\n\",baz", ["foo", "\n", "baz"]], + ["foo,,baz", ["foo", nil, "baz"]], + ["foo,bar", ["foo", "bar"]], + ["foo,\"\r\n\n\",baz", ["foo", "\r\n\n", "baz"]], + ["foo,\"foo,bar\",baz", ["foo", "foo,bar", "baz"]] ].each do |csv_test| + assert_equal(csv_test.last, CSV.parse_line(csv_test.first)) + end + end + + # From: http://ruby-talk.org/cgi-bin/scat.rb/ruby/ruby-core/6496 + def test_aras_edge_cases + [ [%Q{a,b}, ["a", "b"]], + [%Q{a,"""b"""}, ["a", "\"b\""]], + [%Q{a,"""b"}, ["a", "\"b"]], + [%Q{a,"b"""}, ["a", "b\""]], + [%Q{a,"\nb"""}, ["a", "\nb\""]], + [%Q{a,"""\nb"}, ["a", "\"\nb"]], + [%Q{a,"""\nb\n"""}, ["a", "\"\nb\n\""]], + [%Q{a,"""\nb\n""",\nc}, ["a", "\"\nb\n\"", nil]], + [%Q{a,,,}, ["a", nil, nil, nil]], + [%Q{,}, [nil, nil]], + [%Q{"",""}, ["", ""]], + [%Q{""""}, ["\""]], + [%Q{"""",""}, ["\"",""]], + [%Q{,""}, [nil,""]], + [%Q{,"\r"}, [nil,"\r"]], + [%Q{"\r\n,"}, ["\r\n,"]], + [%Q{"\r\n,",}, ["\r\n,", nil]] ].each do |edge_case| + assert_equal(edge_case.last, CSV.parse_line(edge_case.first)) + end + end + + def test_james_edge_cases + # A read at eof? should return nil. + assert_equal(nil, CSV.parse_line("")) + # + # With Ruby 1.8 CSV it's impossible to tell an empty line from a line + # containing a single +nil+ field. The old CSV library returns + # <tt>[nil]</tt> in these cases, but <tt>Array.new</tt> makes more sense to + # me. + # + assert_equal(Array.new, CSV.parse_line("\n1,2,3\n")) + end + + def test_malformed_csv + assert_raise(CSV::MalformedCSVError) do + CSV.parse_line("1,2\r,3", :row_sep => "\n") + end + + bad_data = <<-END_DATA.gsub(/^ +/, "") + line,1,abc + line,2,"def\nghi" + + line,4,some\rjunk + line,5,jkl + END_DATA + lines = bad_data.to_a + assert_equal(6, lines.size) + assert_match(/\Aline,4/, lines.find { |l| l =~ /some\rjunk/ }) + + csv = CSV.new(bad_data) + begin + loop do + assert_not_nil(csv.shift) + assert_send([csv.lineno, :<, 4]) + end + rescue CSV::MalformedCSVError + assert_equal( "Unquoted fields do not allow \\r or \\n (line 4).", + $!.message ) + end + + assert_raise(CSV::MalformedCSVError) { CSV.parse_line('1,2,"3...') } + + bad_data = <<-END_DATA.gsub(/^ +/, "") + line,1,abc + line,2,"def\nghi" + + line,4,8'10" + line,5,jkl + END_DATA + lines = bad_data.to_a + assert_equal(6, lines.size) + assert_match(/\Aline,4/, lines.find { |l| l =~ /8'10"/ }) + + csv = CSV.new(bad_data) + begin + loop do + assert_not_nil(csv.shift) + assert_send([csv.lineno, :<, 4]) + end + rescue CSV::MalformedCSVError + assert_equal("Unclosed quoted field on line 4.", $!.message) + end + end +end diff --git a/test/csv/tc_csv_writing.rb b/test/csv/tc_csv_writing.rb new file mode 100644 index 0000000000..4677284306 --- /dev/null +++ b/test/csv/tc_csv_writing.rb @@ -0,0 +1,96 @@ +#!/usr/local/bin/ruby -w + +# tc_csv_writing.rb +# +# Created by James Edward Gray II on 2005-10-31. +# Copyright 2005 James Edward Gray II. You can redistribute or modify this code +# under the terms of Ruby's license. + +require "test/unit" + +require "csv" + +class TestCSVWriting < Test::Unit::TestCase + def test_writing + [ ["\t", ["\t"]], + ["foo,\"\"\"\"\"\",baz", ["foo", "\"\"", "baz"]], + ["foo,\"\"\"bar\"\"\",baz", ["foo", "\"bar\"", "baz"]], + ["\"\"\"\n\",\"\"\"\n\"", ["\"\n", "\"\n"]], + ["foo,\"\r\n\",baz", ["foo", "\r\n", "baz"]], + ["\"\"", [""]], + ["foo,\"\"\"\",baz", ["foo", "\"", "baz"]], + ["foo,\"\r.\n\",baz", ["foo", "\r.\n", "baz"]], + ["foo,\"\r\",baz", ["foo", "\r", "baz"]], + ["foo,\"\",baz", ["foo", "", "baz"]], + ["\",\"", [","]], + ["foo", ["foo"]], + [",,", [nil, nil, nil]], + [",", [nil, nil]], + ["foo,\"\n\",baz", ["foo", "\n", "baz"]], + ["foo,,baz", ["foo", nil, "baz"]], + ["\"\"\"\r\",\"\"\"\r\"", ["\"\r", "\"\r"]], + ["\",\",\",\"", [",", ","]], + ["foo,bar,", ["foo", "bar", nil]], + [",foo,bar", [nil, "foo", "bar"]], + ["foo,bar", ["foo", "bar"]], + [";", [";"]], + ["\t,\t", ["\t", "\t"]], + ["foo,\"\r\n\r\",baz", ["foo", "\r\n\r", "baz"]], + ["foo,\"\r\n\n\",baz", ["foo", "\r\n\n", "baz"]], + ["foo,\"foo,bar\",baz", ["foo", "foo,bar", "baz"]], + [";,;", [";", ";"]], + ["foo,\"\"\"\"\"\",baz", ["foo", "\"\"", "baz"]], + ["foo,\"\"\"bar\"\"\",baz", ["foo", "\"bar\"", "baz"]], + ["foo,\"\r\n\",baz", ["foo", "\r\n", "baz"]], + ["\"\"", [""]], + ["foo,\"\"\"\",baz", ["foo", "\"", "baz"]], + ["foo,\"\r.\n\",baz", ["foo", "\r.\n", "baz"]], + ["foo,\"\r\",baz", ["foo", "\r", "baz"]], + ["foo,\"\",baz", ["foo", "", "baz"]], + ["foo", ["foo"]], + [",,", [nil, nil, nil]], + [",", [nil, nil]], + ["foo,\"\n\",baz", ["foo", "\n", "baz"]], + ["foo,,baz", ["foo", nil, "baz"]], + ["foo,bar", ["foo", "bar"]], + ["foo,\"\r\n\n\",baz", ["foo", "\r\n\n", "baz"]], + ["foo,\"foo,bar\",baz", ["foo", "foo,bar", "baz"]], + [%Q{a,b}, ["a", "b"]], + [%Q{a,"""b"""}, ["a", "\"b\""]], + [%Q{a,"""b"}, ["a", "\"b"]], + [%Q{a,"b"""}, ["a", "b\""]], + [%Q{a,"\nb"""}, ["a", "\nb\""]], + [%Q{a,"""\nb"}, ["a", "\"\nb"]], + [%Q{a,"""\nb\n"""}, ["a", "\"\nb\n\""]], + [%Q{a,"""\nb\n""",}, ["a", "\"\nb\n\"", nil]], + [%Q{a,,,}, ["a", nil, nil, nil]], + [%Q{,}, [nil, nil]], + [%Q{"",""}, ["", ""]], + [%Q{""""}, ["\""]], + [%Q{"""",""}, ["\"",""]], + [%Q{,""}, [nil,""]], + [%Q{,"\r"}, [nil,"\r"]], + [%Q{"\r\n,"}, ["\r\n,"]], + [%Q{"\r\n,",}, ["\r\n,", nil]] ].each do |test_case| + assert_equal(test_case.first + $/, CSV.generate_line(test_case.last)) + end + end + + def test_col_sep + assert_equal( "a;b;;c\n", CSV.generate_line( ["a", "b", nil, "c"], + :col_sep => ";" ) ) + assert_equal( "a\tb\t\tc\n", CSV.generate_line( ["a", "b", nil, "c"], + :col_sep => "\t" ) ) + end + + def test_row_sep + assert_equal( "a,b,,c\r\n", CSV.generate_line( ["a", "b", nil, "c"], + :row_sep => "\r\n" ) ) + end + + def test_force_quotes + assert_equal( %Q{"1","b","","already ""quoted"""\n}, + CSV.generate_line( [1, "b", nil, %Q{already "quoted"}], + :force_quotes => true ) ) + end +end diff --git a/test/csv/tc_data_converters.rb b/test/csv/tc_data_converters.rb new file mode 100644 index 0000000000..24c6b6b76f --- /dev/null +++ b/test/csv/tc_data_converters.rb @@ -0,0 +1,260 @@ +#!/usr/local/bin/ruby -w + +# tc_data_converters.rb +# +# Created by James Edward Gray II on 2005-10-31. +# Copyright 2005 James Edward Gray II. You can redistribute or modify this code +# under the terms of Ruby's license. + +require "test/unit" + +require "csv" + +class TestDataConverters < Test::Unit::TestCase + def setup + @data = "Numbers,:integer,1,:float,3.015" + @parser = CSV.new(@data) + + @custom = lambda { |field| field =~ /\A:(\S.*?)\s*\Z/ ? $1.to_sym : field } + + @win_safe_time_str = Time.now.strftime("%a %b %d %H:%M:%S %Y") + end + + def test_builtin_integer_converter + # does convert + [-5, 1, 10000000000].each do |n| + assert_equal(n, CSV::Converters[:integer][n.to_s]) + end + + # does not convert + (%w{junk 1.0} + [""]).each do |str| + assert_equal(str, CSV::Converters[:integer][str]) + end + end + + def test_builtin_float_converter + # does convert + [-5.1234, 0, 2.3e-11].each do |n| + assert_equal(n, CSV::Converters[:float][n.to_s]) + end + + # does not convert + (%w{junk 1..0 .015F} + [""]).each do |str| + assert_equal(str, CSV::Converters[:float][str]) + end + end + + def test_builtin_date_converter + # does convert + assert_instance_of( + Date, + CSV::Converters[:date][@win_safe_time_str.sub(/\d+:\d+:\d+ /, "")] + ) + + # does not convert + assert_instance_of(String, CSV::Converters[:date]["junk"]) + end + + def test_builtin_date_time_converter + # does convert + assert_instance_of( DateTime, + CSV::Converters[:date_time][@win_safe_time_str] ) + + # does not convert + assert_instance_of(String, CSV::Converters[:date_time]["junk"]) + end + + def test_convert_with_builtin + # setup parser... + assert(@parser.respond_to?(:convert)) + assert_nothing_raised(Exception) { @parser.convert(:integer) } + + # and use + assert_equal(["Numbers", ":integer", 1, ":float", "3.015"], @parser.shift) + + setup # reset + + # setup parser... + assert_nothing_raised(Exception) { @parser.convert(:float) } + + # and use + assert_equal(["Numbers", ":integer", 1.0, ":float", 3.015], @parser.shift) + end + + def test_convert_order + # floats first, then integers... + assert_nothing_raised(Exception) do + @parser.convert(:float) + @parser.convert(:integer) + end + + # gets us nothing but floats + assert_equal( [String, String, Float, String, Float], + @parser.shift.map { |field| field.class } ) + + setup # reset + + # integers have precendance... + assert_nothing_raised(Exception) do + @parser.convert(:integer) + @parser.convert(:float) + end + + # gives us proper number conversion + assert_equal( [String, String, Fixnum, String, Float], + @parser.shift.map { |field| field.class } ) + end + + def test_builtin_numeric_combo_converter + # setup parser... + assert_nothing_raised(Exception) { @parser.convert(:numeric) } + + # and use + assert_equal( [String, String, Fixnum, String, Float], + @parser.shift.map { |field| field.class } ) + end + + def test_builtin_all_nested_combo_converter + # setup parser... + @data << ",#{@win_safe_time_str}" # add a DateTime field + @parser = CSV.new(@data) # reset parser + assert_nothing_raised(Exception) { @parser.convert(:all) } + + # and use + assert_equal( [String, String, Fixnum, String, Float, DateTime], + @parser.shift.map { |field| field.class } ) + end + + def test_convert_with_custom_code + # define custom converter... + assert_nothing_raised(Exception) do + @parser.convert { |field| field =~ /\A:(\S.*?)\s*\Z/ ? $1.to_sym : field } + end + + # and use + assert_equal(["Numbers", :integer, "1", :float, "3.015"], @parser.shift) + + setup # reset + + # mix built-in and custom... + assert_nothing_raised(Exception) { @parser.convert(:numeric) } + assert_nothing_raised(Exception) { @parser.convert(&@custom) } + + # and use + assert_equal(["Numbers", :integer, 1, :float, 3.015], @parser.shift) + end + + def test_convert_with_custom_code_using_field_info + # define custom converter that uses field information... + assert_nothing_raised(Exception) do + @parser.convert do |field, info| + assert_equal(1, info.line) + info.index == 4 ? Float(field).floor : field + end + end + + # and use + assert_equal(["Numbers", ":integer", "1", ":float", 3], @parser.shift) + end + + def test_convert_with_custom_code_using_field_info_header + @parser = CSV.new(@data, :headers => %w{one two three four five}) + + # define custom converter that uses field header information... + assert_nothing_raised(Exception) do + @parser.convert do |field, info| + info.header == "three" ? Integer(field) * 100 : field + end + end + + # and use + assert_equal( ["Numbers", ":integer", 100, ":float", "3.015"], + @parser.shift.fields ) + end + + def test_shortcut_interface + assert_equal( ["Numbers", ":integer", 1, ":float", 3.015], + CSV.parse_line(@data, :converters => :numeric) ) + + assert_equal( ["Numbers", ":integer", 1, ":float", 3.015], + CSV.parse_line(@data, :converters => [:integer, :float]) ) + + assert_equal( ["Numbers", :integer, 1, :float, 3.015], + CSV.parse_line(@data, :converters => [:numeric, @custom]) ) + end + + def test_unconverted_fields + [ [ @data, + ["Numbers", :integer, 1, :float, 3.015], + %w{Numbers :integer 1 :float 3.015} ], + ["\n", Array.new, Array.new] ].each do |test, fields, unconverted| + row = nil + assert_nothing_raised(Exception) do + row = CSV.parse_line( test, + :converters => [:numeric, @custom], + :unconverted_fields => true ) + end + assert_not_nil(row) + assert_equal(fields, row) + assert_respond_to(row, :unconverted_fields) + assert_equal(unconverted, row.unconverted_fields) + end + + data = <<-END_CSV.gsub(/^\s+/, "") + first,second,third + 1,2,3 + END_CSV + row = nil + assert_nothing_raised(Exception) do + row = CSV.parse_line( data, + :converters => :numeric, + :unconverted_fields => true, + :headers => :first_row ) + end + assert_not_nil(row) + assert_equal([["first", 1], ["second", 2], ["third", 3]], row.to_a) + assert_respond_to(row, :unconverted_fields) + assert_equal(%w{1 2 3}, row.unconverted_fields) + + assert_nothing_raised(Exception) do + row = CSV.parse_line( data, + :converters => :numeric, + :unconverted_fields => true, + :headers => :first_row, + :return_headers => true ) + end + assert_not_nil(row) + assert_equal( [%w{first first}, %w{second second}, %w{third third}], + row.to_a ) + assert_respond_to(row, :unconverted_fields) + assert_equal(%w{first second third}, row.unconverted_fields) + + assert_nothing_raised(Exception) do + row = CSV.parse_line( data, + :converters => :numeric, + :unconverted_fields => true, + :headers => :first_row, + :return_headers => true, + :header_converters => :symbol ) + end + assert_not_nil(row) + assert_equal( [[:first, "first"], [:second, "second"], [:third, "third"]], + row.to_a ) + assert_respond_to(row, :unconverted_fields) + assert_equal(%w{first second third}, row.unconverted_fields) + + assert_nothing_raised(Exception) do + row = CSV.parse_line( data, + :converters => :numeric, + :unconverted_fields => true, + :headers => %w{my new headers}, + :return_headers => true, + :header_converters => :symbol ) + end + assert_not_nil(row) + assert_equal( [[:my, "my"], [:new, "new"], [:headers, "headers"]], + row.to_a ) + assert_respond_to(row, :unconverted_fields) + assert_equal(Array.new, row.unconverted_fields) + end +end diff --git a/test/csv/tc_features.rb b/test/csv/tc_features.rb new file mode 100644 index 0000000000..6766839e10 --- /dev/null +++ b/test/csv/tc_features.rb @@ -0,0 +1,177 @@ +#!/usr/local/bin/ruby -w + +# tc_features.rb +# +# Created by James Edward Gray II on 2005-10-31. +# Copyright 2005 James Edward Gray II. You can redistribute or modify this code +# under the terms of Ruby's license. + +require "test/unit" +require "zlib" + +require "csv" + +class TestCSVFeatures < Test::Unit::TestCase + TEST_CASES = [ [%Q{a,b}, ["a", "b"]], + [%Q{a,"""b"""}, ["a", "\"b\""]], + [%Q{a,"""b"}, ["a", "\"b"]], + [%Q{a,"b"""}, ["a", "b\""]], + [%Q{a,"\nb"""}, ["a", "\nb\""]], + [%Q{a,"""\nb"}, ["a", "\"\nb"]], + [%Q{a,"""\nb\n"""}, ["a", "\"\nb\n\""]], + [%Q{a,"""\nb\n""",\nc}, ["a", "\"\nb\n\"", nil]], + [%Q{a,,,}, ["a", nil, nil, nil]], + [%Q{,}, [nil, nil]], + [%Q{"",""}, ["", ""]], + [%Q{""""}, ["\""]], + [%Q{"""",""}, ["\"",""]], + [%Q{,""}, [nil,""]], + [%Q{,"\r"}, [nil,"\r"]], + [%Q{"\r\n,"}, ["\r\n,"]], + [%Q{"\r\n,",}, ["\r\n,", nil]] ] + + def setup + @sample_data = <<-END_DATA.gsub(/^ +/, "") + line,1,abc + line,2,"def\nghi" + + line,4,jkl + END_DATA + @csv = CSV.new(@sample_data) + end + + def test_col_sep + [";", "\t"].each do |sep| + TEST_CASES.each do |test_case| + assert_equal( test_case.last.map { |t| t.tr(",", sep) unless t.nil? }, + CSV.parse_line( test_case.first.tr(",", sep), + :col_sep => sep ) ) + end + end + assert_equal([",,,", nil], CSV.parse_line(",,,;", :col_sep => ";")) + end + + def test_row_sep + assert_raise(CSV::MalformedCSVError) do + CSV.parse_line("1,2,3\n,4,5\r\n", :row_sep => "\r\n") + end + assert_equal( ["1", "2", "3\n", "4", "5"], + CSV.parse_line(%Q{1,2,"3\n",4,5\r\n}, :row_sep => "\r\n")) + end + + def test_quote_char + TEST_CASES.each do |test_case| + assert_equal( test_case.last.map { |t| t.tr('"', "'") unless t.nil? }, + CSV.parse_line( test_case.first.tr('"', "'"), + :quote_char => "'" ) ) + end + end + + def test_row_sep_auto_discovery + ["\r\n", "\n", "\r"].each do |line_end| + data = "1,2,3#{line_end}4,5#{line_end}" + discovered = CSV.new(data).instance_eval { @row_sep } + assert_equal(line_end, discovered) + end + + assert_equal("\n", CSV.new("\n\r\n\r").instance_eval { @row_sep }) + + assert_equal($/, CSV.new("").instance_eval { @row_sep }) + + assert_equal($/, CSV.new(STDERR).instance_eval { @row_sep }) + end + + def test_lineno + assert_equal(5, @sample_data.to_a.size) + + 4.times do |line_count| + assert_equal(line_count, @csv.lineno) + assert_not_nil(@csv.shift) + assert_equal(line_count + 1, @csv.lineno) + end + assert_nil(@csv.shift) + end + + def test_readline + test_lineno + + @csv.rewind + + test_lineno + end + + def test_unknown_options + assert_raise(ArgumentError) { CSV.new(String.new, :unknown => :error) } + end + + def test_skip_blanks + assert_equal(4, @csv.to_a.size) + + @csv = CSV.new(@sample_data, :skip_blanks => true) + + count = 0 + @csv.each do |row| + count += 1 + assert_equal("line", row.first) + end + assert_equal(3, count) + end + + # reported by Kev Jackson + def test_failing_to_escape_col_sep_bug_fix + assert_nothing_raised(Exception) { CSV.new(String.new, :col_sep => "|") } + end + + # reported by Chris Roos + def test_failing_to_reset_headers_in_rewind_bug_fix + csv = CSV.new("forename,surname", :headers => true, :return_headers => true) + csv.each { |row| assert row.header_row? } + csv.rewind + csv.each { |row| assert row.header_row? } + end + + # reported by Dave Burt + def test_leading_empty_fields_with_multibyte_col_sep_bug_fix + data = <<-END_DATA.gsub(/^\s+/, "") + <=><=>A<=>B<=>C + 1<=>2<=>3 + END_DATA + parsed = CSV.parse(data, :col_sep => "<=>") + assert_equal([[nil, nil, "A", "B", "C"], ["1", "2", "3"]], parsed) + end + + def test_gzip_reader_bug_fix + zipped = nil + assert_nothing_raised(NoMethodError) do + zipped = CSV.new( + Zlib::GzipReader.open( + File.join(File.dirname(__FILE__), "line_endings.gz") + ) + ) + end + assert_equal("\r\n", zipped.instance_eval { @row_sep }) + end + + def test_gzip_writer_bug_fix + file = File.join(File.dirname(__FILE__), "temp.gz") + zipped = nil + assert_nothing_raised(NoMethodError) do + zipped = CSV.new(Zlib::GzipWriter.open(file)) + end + zipped << %w[one two three] + zipped << [1, 2, 3] + zipped.close + + assert( Zlib::GzipReader.open(file) { |f| f.read }. + include?($INPUT_RECORD_SEPARATOR), + "@row_sep did not default" ) + File.unlink(file) + end + + def test_version + assert_not_nil(CSV::VERSION) + assert_instance_of(String, CSV::VERSION) + assert(CSV::VERSION.frozen?) + assert_match(/\A\d\.\d\.\d\Z/, CSV::VERSION) + end +end diff --git a/test/csv/tc_headers.rb b/test/csv/tc_headers.rb new file mode 100644 index 0000000000..74e2f54ad4 --- /dev/null +++ b/test/csv/tc_headers.rb @@ -0,0 +1,261 @@ +#!/usr/local/bin/ruby -w + +# tc_headers.rb +# +# Created by James Edward Gray II on 2005-10-31. +# Copyright 2005 James Edward Gray II. You can redistribute or modify this code +# under the terms of Ruby's license. + +require "test/unit" + +require "csv" + +class TestCSVHeaders < Test::Unit::TestCase + def setup + @data = <<-END_CSV.gsub(/^\s+/, "") + first,second,third + A,B,C + 1,2,3 + END_CSV + end + + def test_first_row + [:first_row, true].each do |setting| # two names for the same setting + # activate headers + csv = nil + assert_nothing_raised(Exception) do + csv = CSV.parse(@data, :headers => setting) + end + + # first data row - skipping headers + row = csv[0] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([%w{first A}, %w{second B}, %w{third C}], row.to_a) + + # second data row + row = csv[1] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([%w{first 1}, %w{second 2}, %w{third 3}], row.to_a) + + # empty + assert_nil(csv[2]) + end + end + + def test_array_of_headers + # activate headers + csv = nil + assert_nothing_raised(Exception) do + csv = CSV.parse(@data, :headers => [:my, :new, :headers]) + end + + # first data row - skipping headers + row = csv[0] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal( [[:my, "first"], [:new, "second"], [:headers, "third"]], + row.to_a ) + + # second data row + row = csv[1] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([[:my, "A"], [:new, "B"], [:headers, "C"]], row.to_a) + + # third data row + row = csv[2] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([[:my, "1"], [:new, "2"], [:headers, "3"]], row.to_a) + + # empty + assert_nil(csv[3]) + + # with return and convert + assert_nothing_raised(Exception) do + csv = CSV.parse(@data, :headers => [:my, :new, :headers], + :return_headers => true, + :header_converters => lambda { |h| h.to_s } ) + end + row = csv[0] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([["my", :my], ["new", :new], ["headers", :headers]], row.to_a) + assert(row.header_row?) + assert(!row.field_row?) + end + + def test_csv_header_string + # activate headers + csv = nil + assert_nothing_raised(Exception) do + csv = CSV.parse(@data, :headers => "my,new,headers") + end + + # first data row - skipping headers + row = csv[0] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([%w{my first}, %w{new second}, %w{headers third}], row.to_a) + + # second data row + row = csv[1] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([%w{my A}, %w{new B}, %w{headers C}], row.to_a) + + # third data row + row = csv[2] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([%w{my 1}, %w{new 2}, %w{headers 3}], row.to_a) + + # empty + assert_nil(csv[3]) + + # with return and convert + assert_nothing_raised(Exception) do + csv = CSV.parse(@data, :headers => "my,new,headers", + :return_headers => true, + :header_converters => :symbol ) + end + row = csv[0] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([[:my, "my"], [:new, "new"], [:headers, "headers"]], row.to_a) + assert(row.header_row?) + assert(!row.field_row?) + end + + def test_return_headers + # activate headers and request they are returned + csv = nil + assert_nothing_raised(Exception) do + csv = CSV.parse(@data, :headers => true, :return_headers => true) + end + + # header row + row = csv[0] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal( [%w{first first}, %w{second second}, %w{third third}], + row.to_a ) + assert(row.header_row?) + assert(!row.field_row?) + + # first data row - skipping headers + row = csv[1] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([%w{first A}, %w{second B}, %w{third C}], row.to_a) + assert(!row.header_row?) + assert(row.field_row?) + + # second data row + row = csv[2] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([%w{first 1}, %w{second 2}, %w{third 3}], row.to_a) + assert(!row.header_row?) + assert(row.field_row?) + + # empty + assert_nil(csv[3]) + end + + def test_converters + # create test data where headers and fields look alike + data = <<-END_MATCHING_CSV.gsub(/^\s+/, "") + 1,2,3 + 1,2,3 + END_MATCHING_CSV + + # normal converters do not affect headers + csv = CSV.parse( data, :headers => true, + :return_headers => true, + :converters => :numeric ) + assert_equal([%w{1 1}, %w{2 2}, %w{3 3}], csv[0].to_a) + assert_equal([["1", 1], ["2", 2], ["3", 3]], csv[1].to_a) + assert_nil(csv[2]) + + # header converters do affect headers (only) + assert_nothing_raised(Exception) do + csv = CSV.parse( data, :headers => true, + :return_headers => true, + :converters => :numeric, + :header_converters => :symbol ) + end + assert_equal([[:"1", "1"], [:"2", "2"], [:"3", "3"]], csv[0].to_a) + assert_equal([[:"1", 1], [:"2", 2], [:"3", 3]], csv[1].to_a) + assert_nil(csv[2]) + end + + def test_builtin_downcase_converter + csv = CSV.parse( "One,TWO Three", :headers => true, + :return_headers => true, + :header_converters => :downcase ) + assert_equal(%w{one two\ three}, csv.headers) + end + + def test_builtin_symbol_converter + csv = CSV.parse( "One,TWO Three", :headers => true, + :return_headers => true, + :header_converters => :symbol ) + assert_equal([:one, :two_three], csv.headers) + end + + def test_custom_converter + converter = lambda { |header| header.tr(" ", "_") } + csv = CSV.parse( "One,TWO Three", + :headers => true, + :return_headers => true, + :header_converters => converter ) + assert_equal(%w{One TWO_Three}, csv.headers) + end + + def test_table_support + csv = nil + assert_nothing_raised(Exception) do + csv = CSV.parse(@data, :headers => true) + end + + assert_instance_of(CSV::Table, csv) + end + + def test_skip_blanks + @data = <<-END_CSV.gsub(/^ +/, "") + + + A,B,C + + 1,2,3 + + + + END_CSV + + expected = [%w[1 2 3]] + CSV.parse(@data, :headers => true, :skip_blanks => true) do |row| + assert_equal(expected.shift, row.fields) + end + + expected = [%w[A B C], %w[1 2 3]] + CSV.parse( @data, + :headers => true, + :return_headers => true, + :skip_blanks => true ) do |row| + assert_equal(expected.shift, row.fields) + end + end + + def test_blank_row_bug_fix + @data += "\n#{@data}" # add a blank row + + # ensure that everything returned is a Row object + CSV.parse(@data, :headers => true) do |row| + assert_instance_of(CSV::Row, row) + end + end +end diff --git a/test/csv/tc_interface.rb b/test/csv/tc_interface.rb new file mode 100644 index 0000000000..e8cc920f9d --- /dev/null +++ b/test/csv/tc_interface.rb @@ -0,0 +1,235 @@ +#!/usr/local/bin/ruby -w + +# tc_interface.rb +# +# Created by James Edward Gray II on 2005-10-31. +# Copyright 2005 James Edward Gray II. You can redistribute or modify this code +# under the terms of Ruby's license. + +require "test/unit" + +require "csv" + +class TestCSVInterface < Test::Unit::TestCase + def setup + @path = File.join(File.dirname(__FILE__), "temp_test_data.csv") + + File.open(@path, "w") do |file| + file << "1\t2\t3\r\n" + file << "4\t5\r\n" + end + + @expected = [%w{1 2 3}, %w{4 5}] + end + + def teardown + File.unlink(@path) + end + + ### Test Read Interface ### + + def test_foreach + CSV.foreach(@path, :col_sep => "\t", :row_sep => "\r\n") do |row| + assert_equal(@expected.shift, row) + end + end + + def test_open_and_close + csv = CSV.open(@path, "r+", :col_sep => "\t", :row_sep => "\r\n") + assert_not_nil(csv) + assert_instance_of(CSV, csv) + assert_equal(false, csv.closed?) + csv.close + assert(csv.closed?) + + ret = CSV.open(@path) do |csv| + assert_instance_of(CSV, csv) + "Return value." + end + assert(csv.closed?) + assert_equal("Return value.", ret) + end + + def test_parse + data = File.read(@path) + assert_equal( @expected, + CSV.parse(data, :col_sep => "\t", :row_sep => "\r\n") ) + + CSV.parse(data, :col_sep => "\t", :row_sep => "\r\n") do |row| + assert_equal(@expected.shift, row) + end + end + + def test_parse_line + row = CSV.parse_line("1;2;3", :col_sep => ";") + assert_not_nil(row) + assert_instance_of(Array, row) + assert_equal(%w{1 2 3}, row) + + # shortcut interface + row = "1;2;3".parse_csv(:col_sep => ";") + assert_not_nil(row) + assert_instance_of(Array, row) + assert_equal(%w{1 2 3}, row) + end + + def test_read_and_readlines + assert_equal( @expected, + CSV.read(@path, :col_sep => "\t", :row_sep => "\r\n") ) + assert_equal( @expected, + CSV.readlines(@path, :col_sep => "\t", :row_sep => "\r\n") ) + + + data = CSV.open(@path, :col_sep => "\t", :row_sep => "\r\n") do |csv| + csv.read + end + assert_equal(@expected, data) + data = CSV.open(@path, :col_sep => "\t", :row_sep => "\r\n") do |csv| + csv.readlines + end + assert_equal(@expected, data) + end + + def test_table + table = CSV.table(@path, :col_sep => "\t", :row_sep => "\r\n") + assert_instance_of(CSV::Table, table) + assert_equal([[:"1", :"2", :"3"], [4, 5, nil]], table.to_a) + end + + def test_shift # aliased as gets() and readline() + CSV.open(@path, "r+", :col_sep => "\t", :row_sep => "\r\n") do |csv| + assert_equal(@expected.shift, csv.shift) + assert_equal(@expected.shift, csv.shift) + assert_equal(nil, csv.shift) + end + end + + ### Test Write Interface ### + + def test_generate + str = CSV.generate do |csv| # default empty String + assert_instance_of(CSV, csv) + assert_equal(csv, csv << [1, 2, 3]) + assert_equal(csv, csv << [4, nil, 5]) + end + assert_not_nil(str) + assert_instance_of(String, str) + assert_equal("1,2,3\n4,,5\n", str) + + CSV.generate(str) do |csv| # appending to a String + assert_equal(csv, csv << ["last", %Q{"row"}]) + end + assert_equal(%Q{1,2,3\n4,,5\nlast,"""row"""\n}, str) + end + + def test_generate_line + line = CSV.generate_line(%w{1 2 3}, :col_sep => ";") + assert_not_nil(line) + assert_instance_of(String, line) + assert_equal("1;2;3\n", line) + + # shortcut interface + line = %w{1 2 3}.to_csv(:col_sep => ";") + assert_not_nil(line) + assert_instance_of(String, line) + assert_equal("1;2;3\n", line) + end + + def test_write_header_detection + File.unlink(@path) + + headers = %w{a b c} + CSV.open(@path, "w", :headers => true) do |csv| + csv << headers + csv << %w{1 2 3} + assert_equal(headers, csv.instance_variable_get(:@headers)) + end + end + + def test_write_lineno + File.unlink(@path) + + CSV.open(@path, "w") do |csv| + lines = 20 + lines.times { csv << %w{a b c} } + assert_equal(lines, csv.lineno) + end + end + + def test_write_hash + File.unlink(@path) + + lines = [{:a => 1, :b => 2, :c => 3}, {:a => 4, :b => 5, :c => 6}] + CSV.open( @path, "w", :headers => true, + :converters => :all, + :header_converters => :symbol ) do |csv| + csv << lines.first.keys + lines.each { |line| csv << line } + end + CSV.open( @path, "w", :headers => true, + :converters => :all, + :header_converters => :symbol ) do |csv| + csv.each { |line| assert_equal(lines.shift, line.to_hash) } + end + end + + def test_append # aliased add_row() and puts() + File.unlink(@path) + + CSV.open(@path, "w", :col_sep => "\t", :row_sep => "\r\n") do |csv| + @expected.each { |row| csv << row } + end + + test_shift + + # same thing using CSV::Row objects + File.unlink(@path) + + CSV.open(@path, "w", :col_sep => "\t", :row_sep => "\r\n") do |csv| + @expected.each { |row| csv << CSV::Row.new(Array.new, row) } + end + + test_shift + end + + ### Test Read and Write Interface ### + + def test_filter + assert_respond_to(CSV, :filter) + + expected = [[1, 2, 3], [4, 5]] + CSV.filter( "1;2;3\n4;5\n", (result = String.new), + :in_col_sep => ";", :out_col_sep => ",", + :converters => :all ) do |row| + assert_equal(row, expected.shift) + row.map! { |n| n * 2 } + row << "Added\r" + end + assert_equal("2,4,6,\"Added\r\"\n8,10,\"Added\r\"\n", result) + end + + def test_instance + csv = String.new + + first = nil + assert_nothing_raised(Exception) do + first = CSV.instance(csv, :col_sep => ";") + first << %w{a b c} + end + + assert_equal("a;b;c\n", csv) + + second = nil + assert_nothing_raised(Exception) do + second = CSV.instance(csv, :col_sep => ";") + second << [1, 2, 3] + end + + assert_equal(first.object_id, second.object_id) + assert_equal("a;b;c\n1;2;3\n", csv) + + # shortcuts + assert_equal(STDOUT, CSV.instance.instance_eval { @io }) + assert_equal(STDOUT, CSV { |csv| csv.instance_eval { @io } }) + end +end diff --git a/test/csv/tc_row.rb b/test/csv/tc_row.rb new file mode 100644 index 0000000000..a9b7f042b2 --- /dev/null +++ b/test/csv/tc_row.rb @@ -0,0 +1,289 @@ +#!/usr/local/bin/ruby -w + +# tc_row.rb +# +# Created by James Edward Gray II on 2005-10-31. +# Copyright 2005 James Edward Gray II. You can redistribute or modify this code +# under the terms of Ruby's license. + +require "test/unit" + +require "csv" + +class TestCSVRow < Test::Unit::TestCase + def setup + @row = CSV::Row.new(%w{A B C A A}, [1, 2, 3, 4]) + end + + def test_initialize + # basic + row = CSV::Row.new(%w{A B C}, [1, 2, 3]) + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([["A", 1], ["B", 2], ["C", 3]], row.to_a) + + # missing headers + row = CSV::Row.new(%w{A}, [1, 2, 3]) + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([["A", 1], [nil, 2], [nil, 3]], row.to_a) + + # missing fields + row = CSV::Row.new(%w{A B C}, [1, 2]) + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([["A", 1], ["B", 2], ["C", nil]], row.to_a) + end + + def test_row_type + # field rows + row = CSV::Row.new(%w{A B C}, [1, 2, 3]) # implicit + assert(!row.header_row?) + assert(row.field_row?) + row = CSV::Row.new(%w{A B C}, [1, 2, 3], false) # explicit + assert(!row.header_row?) + assert(row.field_row?) + + # header row + row = CSV::Row.new(%w{A B C}, [1, 2, 3], true) + assert(row.header_row?) + assert(!row.field_row?) + end + + def test_headers + assert_equal(%w{A B C A A}, @row.headers) + end + + def test_field + # by name + assert_equal(2, @row.field("B")) + assert_equal(2, @row["B"]) # alias + + # by index + assert_equal(3, @row.field(2)) + + # missing + assert_nil(@row.field("Missing")) + assert_nil(@row.field(10)) + + # minimum index + assert_equal(1, @row.field("A")) + assert_equal(1, @row.field("A", 0)) + assert_equal(4, @row.field("A", 1)) + assert_equal(4, @row.field("A", 2)) + assert_equal(4, @row.field("A", 3)) + assert_equal(nil, @row.field("A", 4)) + assert_equal(nil, @row.field("A", 5)) + end + + def test_set_field + # set field by name + assert_equal(100, @row["A"] = 100) + + # set field by index + assert_equal(300, @row[3] = 300) + + # set field by name and minimum index + assert_equal([:a, :b, :c], @row["A", 4] = [:a, :b, :c]) + + # verify the changes + assert_equal( [ ["A", 100], + ["B", 2], + ["C", 3], + ["A", 300], + ["A", [:a, :b, :c]] ], @row.to_a ) + + # assigning an index past the end + assert_equal("End", @row[10] = "End") + assert_equal( [ ["A", 100], + ["B", 2], + ["C", 3], + ["A", 300], + ["A", [:a, :b, :c]], + [nil, nil], + [nil, nil], + [nil, nil], + [nil, nil], + [nil, nil], + [nil, "End"] ], @row.to_a ) + + # assigning a new field by header + assert_equal("New", @row[:new] = "New") + assert_equal( [ ["A", 100], + ["B", 2], + ["C", 3], + ["A", 300], + ["A", [:a, :b, :c]], + [nil, nil], + [nil, nil], + [nil, nil], + [nil, nil], + [nil, nil], + [nil, "End"], + [:new, "New"] ], @row.to_a ) + end + + def test_append + # add a value + assert_equal(@row, @row << "Value") + assert_equal( [ ["A", 1], + ["B", 2], + ["C", 3], + ["A", 4], + ["A", nil], + [nil, "Value"] ], @row.to_a ) + + # add a pair + assert_equal(@row, @row << %w{Header Field}) + assert_equal( [ ["A", 1], + ["B", 2], + ["C", 3], + ["A", 4], + ["A", nil], + [nil, "Value"], + %w{Header Field} ], @row.to_a ) + + # a pair with Hash syntax + assert_equal(@row, @row << {:key => :value}) + assert_equal( [ ["A", 1], + ["B", 2], + ["C", 3], + ["A", 4], + ["A", nil], + [nil, "Value"], + %w{Header Field}, + [:key, :value] ], @row.to_a ) + + # multiple fields at once + assert_equal(@row, @row.push(100, 200, [:last, 300])) + assert_equal( [ ["A", 1], + ["B", 2], + ["C", 3], + ["A", 4], + ["A", nil], + [nil, "Value"], + %w{Header Field}, + [:key, :value], + [nil, 100], + [nil, 200], + [:last, 300] ], @row.to_a ) + end + + def test_delete + # by index + assert_equal(["B", 2], @row.delete(1)) + + # by header + assert_equal(["C", 3], @row.delete("C")) + + # using a block + assert_equal(@row, @row.delete_if { |h, f| h == "A" and not f.nil? }) + assert_equal([["A", nil]], @row.to_a) + end + + def test_fields + # all fields + assert_equal([1, 2, 3, 4, nil], @row.fields) + + # by header + assert_equal([1, 3], @row.fields("A", "C")) + + # by index + assert_equal([2, 3, nil], @row.fields(1, 2, 10)) + + # by both + assert_equal([2, 3, 4], @row.fields("B", "C", 3)) + + # with minimum indices + assert_equal([2, 3, 4], @row.fields("B", "C", ["A", 3])) + + # by header range + assert_equal([2, 3], @row.values_at("B".."C")) + end + + def test_index + # basic usage + assert_equal(0, @row.index("A")) + assert_equal(1, @row.index("B")) + assert_equal(2, @row.index("C")) + assert_equal(nil, @row.index("Z")) + + # with minimum index + assert_equal(0, @row.index("A")) + assert_equal(0, @row.index("A", 0)) + assert_equal(3, @row.index("A", 1)) + assert_equal(3, @row.index("A", 2)) + assert_equal(3, @row.index("A", 3)) + assert_equal(4, @row.index("A", 4)) + assert_equal(nil, @row.index("A", 5)) + end + + def test_queries + # headers + assert(@row.header?("A")) + assert(@row.header?("C")) + assert(!@row.header?("Z")) + assert(@row.include?("A")) # alias + + # fields + assert(@row.field?(4)) + assert(@row.field?(nil)) + assert(!@row.field?(10)) + end + + def test_each + # array style + ary = @row.to_a + @row.each do |pair| + assert_equal(ary.first.first, pair.first) + assert_equal(ary.shift.last, pair.last) + end + + # hash style + ary = @row.to_a + @row.each do |header, field| + assert_equal(ary.first.first, header) + assert_equal(ary.shift.last, field) + end + + # verify that we can chain the call + assert_equal(@row, @row.each { }) + end + + def test_enumerable + assert_equal( [["A", 1], ["A", 4], ["A", nil]], + @row.select { |pair| pair.first == "A" } ) + + assert_equal(10, @row.inject(0) { |sum, (header, n)| sum + (n || 0) }) + end + + def test_to_a + row = CSV::Row.new(%w{A B C}, [1, 2, 3]).to_a + assert_instance_of(Array, row) + row.each do |pair| + assert_instance_of(Array, pair) + assert_equal(2, pair.size) + end + assert_equal([["A", 1], ["B", 2], ["C", 3]], row) + end + + def test_to_hash + assert_equal({"A" => nil, "B" => 2, "C" => 3}, @row.to_hash) + end + + def test_to_csv + # normal conversion + assert_equal("1,2,3,4,\n", @row.to_csv) + assert_equal("1,2,3,4,\n", @row.to_s) # alias + + # with options + assert_equal( "1|2|3|4|\r\n", + @row.to_csv(:col_sep => "|", :row_sep => "\r\n") ) + end + + def test_array_delegation + assert(!@row.empty?, "Row was empty.") + + assert_equal([@row.headers.size, @row.fields.size].max, @row.size) + end +end diff --git a/test/csv/tc_serialization.rb b/test/csv/tc_serialization.rb new file mode 100644 index 0000000000..45e26bc0b5 --- /dev/null +++ b/test/csv/tc_serialization.rb @@ -0,0 +1,155 @@ +#!/usr/local/bin/ruby -w + +# tc_serialization.rb +# +# Created by James Edward Gray II on 2005-10-31. +# Copyright 2005 James Edward Gray II. You can redistribute or modify this code +# under the terms of Ruby's license. + +require "test/unit" + +require "csv" + +# An example of how to provide custom CSV serialization. +class Hash + def self.csv_load( meta, headers, fields ) + self[*headers.zip(fields).flatten.map { |e| eval(e) }] + end + + def csv_headers + keys.map { |key| key.inspect } + end + + def csv_dump( headers ) + headers.map { |header| fetch(eval(header)).inspect } + end +end + +class TestSerialization < Test::Unit::TestCase + + ### Classes Used to Test Serialization ### + + class ReadOnlyName + def initialize( first, last ) + @first, @last = first, last + end + + attr_reader :first, :last + + def ==( other ) + %w{first last}.all? { |att| send(att) == other.send(att) } + end + end + + Name = Struct.new(:first, :last) + + class FullName < Name + def initialize( first, last, suffix = nil ) + super(first, last) + + @suffix = suffix + end + + attr_accessor :suffix + + def ==( other ) + %w{first last suffix}.all? { |att| send(att) == other.send(att) } + end + end + + ### Tests ### + + def test_class_dump + @names = [ %w{James Gray}, + %w{Dana Gray}, + %w{Greg Brown} ].map do |first, last| + ReadOnlyName.new(first, last) + end + + assert_nothing_raised(Exception) do + @data = CSV.dump(@names) + end + assert_equal(<<-END_CLASS_DUMP.gsub(/^\s*/, ""), @data) + class,TestSerialization::ReadOnlyName + @first,@last + James,Gray + Dana,Gray + Greg,Brown + END_CLASS_DUMP + end + + def test_struct_dump + @names = [ %w{James Gray}, + %w{Dana Gray}, + %w{Greg Brown} ].map do |first, last| + Name.new(first, last) + end + + assert_nothing_raised(Exception) do + @data = CSV.dump(@names) + end + assert_equal(<<-END_STRUCT_DUMP.gsub(/^\s*/, ""), @data) + class,TestSerialization::Name + first=,last= + James,Gray + Dana,Gray + Greg,Brown + END_STRUCT_DUMP + end + + def test_inherited_struct_dump + @names = [ %w{James Gray II}, + %w{Dana Gray}, + %w{Greg Brown} ].map do |first, last, suffix| + FullName.new(first, last, suffix) + end + + assert_nothing_raised(Exception) do + @data = CSV.dump(@names) + end + assert_equal(<<-END_STRUCT_DUMP.gsub(/^\s*/, ""), @data) + class,TestSerialization::FullName + @suffix,first=,last= + II,James,Gray + ,Dana,Gray + ,Greg,Brown + END_STRUCT_DUMP + end + + def test_load + %w{ test_class_dump + test_struct_dump + test_inherited_struct_dump }.each do |test| + send(test) + CSV.load(@data).each do |loaded| + assert_instance_of(@names.first.class, loaded) + assert_equal(@names.shift, loaded) + end + end + end + + def test_io + test_class_dump + + data_file = File.join(File.dirname(__FILE__), "temp_test_data.csv") + CSV.dump(@names, File.open(data_file, "w")) + + assert(File.exist?(data_file)) + assert_equal(<<-END_IO_DUMP.gsub(/^\s*/, ""), File.read(data_file)) + class,TestSerialization::ReadOnlyName + @first,@last + James,Gray + Dana,Gray + Greg,Brown + END_IO_DUMP + + assert_equal(@names, CSV.load(File.open(data_file))) + + File.unlink(data_file) + end + + def test_custom_dump_and_load + obj = {1 => "simple", :test => Hash} + assert_equal(obj, CSV.load(CSV.dump([obj])).first) + end +end diff --git a/test/csv/tc_table.rb b/test/csv/tc_table.rb new file mode 100644 index 0000000000..028274d97f --- /dev/null +++ b/test/csv/tc_table.rb @@ -0,0 +1,392 @@ +#!/usr/local/bin/ruby -w + +# tc_table.rb +# +# Created by James Edward Gray II on 2005-10-31. +# Copyright 2005 James Edward Gray II. You can redistribute or modify this code +# under the terms of Ruby's license. + +require "test/unit" + +require "csv" + +class TestCSVTable < Test::Unit::TestCase + def setup + @rows = [ CSV::Row.new(%w{A B C}, [1, 2, 3]), + CSV::Row.new(%w{A B C}, [4, 5, 6]), + CSV::Row.new(%w{A B C}, [7, 8, 9]) ] + @table = CSV::Table.new(@rows) + + @header_table = CSV::Table.new( + [CSV::Row.new(%w{A B C}, %w{A B C}, true)] + @rows + ) + end + + def test_initialze + assert_not_nil(@table) + assert_instance_of(CSV::Table, @table) + end + + def test_modes + assert_equal(:col_or_row, @table.mode) + + # non-destructive changes, intended for one shot calls + cols = @table.by_col + assert_equal(:col_or_row, @table.mode) + assert_equal(:col, cols.mode) + assert_equal(@table, cols) + + rows = @table.by_row + assert_equal(:col_or_row, @table.mode) + assert_equal(:row, rows.mode) + assert_equal(@table, rows) + + # destructive mode changing calls + assert_equal(@table, @table.by_row!) + assert_equal(:row, @table.mode) + assert_equal(@table, @table.by_col_or_row!) + assert_equal(:col_or_row, @table.mode) + end + + def test_headers + assert_equal(@rows.first.headers, @table.headers) + end + + def test_index + ################## + ### Mixed Mode ### + ################## + # by row + @rows.each_index { |i| assert_equal(@rows[i], @table[i]) } + assert_equal(nil, @table[100]) # empty row + + # by col + @rows.first.headers.each do |header| + assert_equal(@rows.map { |row| row[header] }, @table[header]) + end + assert_equal([nil] * @rows.size, @table["Z"]) # empty col + + # by cell, row then col + assert_equal(2, @table[0][1]) + assert_equal(6, @table[1]["C"]) + + # by cell, col then row + assert_equal(5, @table["B"][1]) + assert_equal(9, @table["C"][2]) + + # with headers (by col) + assert_equal(["B", 2, 5, 8], @header_table["B"]) + + ################### + ### Column Mode ### + ################### + @table.by_col! + + assert_equal([2, 5, 8], @table[1]) + assert_equal([2, 5, 8], @table["B"]) + + ################ + ### Row Mode ### + ################ + @table.by_row! + + assert_equal(@rows[1], @table[1]) + assert_raise(TypeError) { @table["B"] } + + ############################ + ### One Shot Mode Change ### + ############################ + assert_equal(@rows[1], @table[1]) + assert_equal([2, 5, 8], @table.by_col[1]) + assert_equal(@rows[1], @table[1]) + end + + def test_set_row_or_column + ################## + ### Mixed Mode ### + ################## + # set row + @table[2] = [10, 11, 12] + assert_equal([%w[A B C], [1, 2, 3], [4, 5, 6], [10, 11, 12]], @table.to_a) + + @table[3] = CSV::Row.new(%w[A B C], [13, 14, 15]) + assert_equal( [%w[A B C], [1, 2, 3], [4, 5, 6], [10, 11, 12], [13, 14, 15]], + @table.to_a ) + + # set col + @table["Type"] = "data" + assert_equal( [ %w[A B C Type], + [1, 2, 3, "data"], + [4, 5, 6, "data"], + [10, 11, 12, "data"], + [13, 14, 15, "data"] ], + @table.to_a ) + + @table["Index"] = [1, 2, 3] + assert_equal( [ %w[A B C Type Index], + [1, 2, 3, "data", 1], + [4, 5, 6, "data", 2], + [10, 11, 12, "data", 3], + [13, 14, 15, "data", nil] ], + @table.to_a ) + + @table["B"] = [100, 200] + assert_equal( [ %w[A B C Type Index], + [1, 100, 3, "data", 1], + [4, 200, 6, "data", 2], + [10, nil, 12, "data", 3], + [13, nil, 15, "data", nil] ], + @table.to_a ) + + # verify resulting table + assert_equal(<<-END_RESULT.gsub(/^\s+/, ""), @table.to_csv) + A,B,C,Type,Index + 1,100,3,data,1 + 4,200,6,data,2 + 10,,12,data,3 + 13,,15,data, + END_RESULT + + # with headers + @header_table["Type"] = "data" + assert_equal(%w[Type data data data], @header_table["Type"]) + + ################### + ### Column Mode ### + ################### + @table.by_col! + + @table[1] = [2, 5, 11, 14] + assert_equal( [ %w[A B C Type Index], + [1, 2, 3, "data", 1], + [4, 5, 6, "data", 2], + [10, 11, 12, "data", 3], + [13, 14, 15, "data", nil] ], + @table.to_a ) + + @table["Extra"] = "new stuff" + assert_equal( [ %w[A B C Type Index Extra], + [1, 2, 3, "data", 1, "new stuff"], + [4, 5, 6, "data", 2, "new stuff"], + [10, 11, 12, "data", 3, "new stuff"], + [13, 14, 15, "data", nil, "new stuff"] ], + @table.to_a ) + + ################ + ### Row Mode ### + ################ + @table.by_row! + + @table[1] = (1..6).to_a + assert_equal( [ %w[A B C Type Index Extra], + [1, 2, 3, "data", 1, "new stuff"], + [1, 2, 3, 4, 5, 6], + [10, 11, 12, "data", 3, "new stuff"], + [13, 14, 15, "data", nil, "new stuff"] ], + @table.to_a ) + + assert_raise(TypeError) { @table["Extra"] = nil } + end + + def test_each + ###################### + ### Mixed/Row Mode ### + ###################### + i = 0 + @table.each do |row| + assert_equal(@rows[i], row) + i += 1 + end + + # verify that we can chain the call + assert_equal(@table, @table.each { }) + + ################### + ### Column Mode ### + ################### + @table.by_col! + + headers = @table.headers + @table.each do |header, column| + assert_equal(headers.shift, header) + assert_equal(@table[header], column) + end + + ############################ + ### One Shot Mode Change ### + ############################ + @table.by_col_or_row! + + @table.each { |row| assert_instance_of(CSV::Row, row) } + @table.by_col.each { |tuple| assert_instance_of(Array, tuple) } + @table.each { |row| assert_instance_of(CSV::Row, row) } + end + + def test_enumerable + assert_equal( @rows.values_at(0, 2), + @table.select { |row| (row["B"] % 2).zero? } ) + + assert_equal(@rows[1], @table.find { |row| row["C"] > 5 }) + end + + def test_to_a + assert_equal([%w[A B C], [1, 2, 3], [4, 5, 6], [7, 8, 9]], @table.to_a) + + # with headers + assert_equal( [%w[A B C], [1, 2, 3], [4, 5, 6], [7, 8, 9]], + @header_table.to_a ) + end + + def test_to_csv + csv = <<-END_CSV.gsub(/^\s+/, "") + A,B,C + 1,2,3 + 4,5,6 + 7,8,9 + END_CSV + + # normal conversion + assert_equal(csv, @table.to_csv) + assert_equal(csv, @table.to_s) # alias + + # with options + assert_equal( csv.gsub(",", "|").gsub("\n", "\r\n"), + @table.to_csv(:col_sep => "|", :row_sep => "\r\n") ) + + # with headers + assert_equal(csv, @header_table.to_csv) + end + + def test_append + # verify that we can chain the call + assert_equal(@table, @table << [10, 11, 12]) + + # Array append + assert_equal(CSV::Row.new(%w[A B C], [10, 11, 12]), @table[-1]) + + # Row append + assert_equal(@table, @table << CSV::Row.new(%w[A B C], [13, 14, 15])) + assert_equal(CSV::Row.new(%w[A B C], [13, 14, 15]), @table[-1]) + end + + def test_delete + ################## + ### Mixed Mode ### + ################## + # delete a row + assert_equal(@rows[1], @table.delete(1)) + + # delete a col + assert_equal(@rows.map { |row| row["A"] }, @table.delete("A")) + + # verify resulting table + assert_equal(<<-END_RESULT.gsub(/^\s+/, ""), @table.to_csv) + B,C + 2,3 + 8,9 + END_RESULT + + ################### + ### Column Mode ### + ################### + setup + @table.by_col! + + assert_equal(@rows.map { |row| row[0] }, @table.delete(0)) + assert_equal(@rows.map { |row| row["C"] }, @table.delete("C")) + + # verify resulting table + assert_equal(<<-END_RESULT.gsub(/^\s+/, ""), @table.to_csv) + B + 2 + 5 + 8 + END_RESULT + + ################ + ### Row Mode ### + ################ + setup + @table.by_row! + + assert_equal(@rows[1], @table.delete(1)) + assert_raise(TypeError) { @table.delete("C") } + + # verify resulting table + assert_equal(<<-END_RESULT.gsub(/^\s+/, ""), @table.to_csv) + A,B,C + 1,2,3 + 7,8,9 + END_RESULT + end + + def test_delete_if + ###################### + ### Mixed/Row Mode ### + ###################### + # verify that we can chain the call + assert_equal(@table, @table.delete_if { |row| (row["B"] % 2).zero? }) + + # verify resulting table + assert_equal(<<-END_RESULT.gsub(/^\s+/, ""), @table.to_csv) + A,B,C + 4,5,6 + END_RESULT + + ################### + ### Column Mode ### + ################### + setup + @table.by_col! + + assert_equal(@table, @table.delete_if { |h, v| h > "A" }) + assert_equal(<<-END_RESULT.gsub(/^\s+/, ""), @table.to_csv) + A + 1 + 4 + 7 + END_RESULT + end + + def test_values_at + ################## + ### Mixed Mode ### + ################## + # rows + assert_equal(@rows.values_at(0, 2), @table.values_at(0, 2)) + assert_equal(@rows.values_at(1..2), @table.values_at(1..2)) + + # cols + assert_equal([[1, 3], [4, 6], [7, 9]], @table.values_at("A", "C")) + assert_equal([[2, 3], [5, 6], [8, 9]], @table.values_at("B".."C")) + + ################### + ### Column Mode ### + ################### + @table.by_col! + + assert_equal([[1, 3], [4, 6], [7, 9]], @table.values_at(0, 2)) + assert_equal([[1, 3], [4, 6], [7, 9]], @table.values_at("A", "C")) + + ################ + ### Row Mode ### + ################ + @table.by_row! + + assert_equal(@rows.values_at(0, 2), @table.values_at(0, 2)) + assert_raise(TypeError) { @table.values_at("A", "C") } + + ############################ + ### One Shot Mode Change ### + ############################ + assert_equal(@rows.values_at(0, 2), @table.values_at(0, 2)) + assert_equal([[1, 3], [4, 6], [7, 9]], @table.by_col.values_at(0, 2)) + assert_equal(@rows.values_at(0, 2), @table.values_at(0, 2)) + end + + def test_array_delegation + assert(!@table.empty?, "Table was empty.") + + assert_equal(@rows.size, @table.size) + end +end diff --git a/test/csv/ts_all.rb b/test/csv/ts_all.rb new file mode 100644 index 0000000000..c930523757 --- /dev/null +++ b/test/csv/ts_all.rb @@ -0,0 +1,19 @@ +#!/usr/local/bin/ruby -w + +# ts_all.rb +# +# Created by James Edward Gray II on 2005-10-31. +# Copyright 2005 James Edward Gray II. You can redistribute or modify this code +# under the terms of Ruby's license. + +require "test/unit" + +require "tc_csv_parsing" +require "tc_features" +require "tc_interface" +require "tc_csv_writing" +require "tc_data_converters" +require "tc_row" +require "tc_table" +require "tc_headers" +require "tc_serialization" |